知识图谱实体对齐

flowchart LR
    PAIR["one candidate pair<br/><i>both entities, one state</i>"] --> CALL

    subgraph CALL["one request, four questions"]
        direction TB
        S["<b>Score:</b> how do the two relate?<br/>· different product<br/>· related, but possibly not the same<br/>· same product"]
        N["<b>Nouls:</b> one per compared field<br/>· same name?<br/>· same brewery?<br/>· same style?"]
        %% invisible link: without an edge these two share a rank, which in a TB
        %% subgraph puts them side by side instead of stacked
        S ~~~ N
    end

    S --> R{"round to the<br/>nearest level"}
    R purple_diff@-->|"different"| DROP["leave unlinked"]
    R green_same@-->|"same"| M["assert sameAs"]
    %% the queue is last so the dotted edge below reaches it without crossing
    %% the arrow into `assert sameAs`
    R blue_related@-->|"related"| Q["curator queue"]
    N blue_field@-.->|"which field<br/>they disagree on"| Q
    %% Branch colours (styles.css): node classes and green_/blue_/purple_/orange_ edge ids.
    class M neonGreen
    class Q neonBlue
    class DROP neonPurple

pip install matplotlib ipython 'cooksafe>=0.2.0,<0.3.0'

import json
import os
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path

import matplotlib
import matplotlib.pyplot as plt
from cooksafe import JsonCache, make_playground_link
from IPython.display import Markdown, display
from typesafe_sdk import Noul, Score, TypeSafeClient

matplotlib.use("Agg")  # headless render

TYPESAFE_MODEL = "jev-1.12"
MAX_WORKERS = 6  # small pool; the public endpoint rate-limits above roughly eight

client = TypeSafeClient(
    api_key=os.environ.get(
        "TYPESAFE_API_KEY", "cache-only"
    ),  # keyless kernels replay the cache
    base_url=os.environ.get("TYPESAFE_ENDPOINT"),
    timeout=120.0,
)
json_cache = JsonCache(Path("json_cache.json"))

PAIRS = json.loads(Path("candidate_pairs.json").read_text(encoding="utf-8"))
BY_ID = {pair["id"]: pair for pair in PAIRS}

print(f"{len(PAIRS)} candidate pairs. The first one, as the model will see it:")
print(json.dumps({k: PAIRS[0][k] for k in ("entity_a", "entity_b")}, indent=2)[:420])

450 candidate pairs. The first one, as the model will see it:
{
  "entity_a": {
    "name": "C N Red Imperial Red Ale",
    "brewery": "Redwood Lodge",
    "style": "American Amber / Red Ale",
    "abv": "8.10 %"
  },
  "entity_b": {
    "name": "Kinetic Infrared Imperial Red Ale",
    "brewery": "Kinetic Brewing Company",
    "style": "American Strong Ale",
    "abv": "9.30 %"
  }
}

LEVELS = [
    "They describe two different products.",
    "They describe closely related products that may or may not be the same one: "
    "a variant, a special edition, or a name that could plausibly refer to either.",
    "They describe one and the same product.",
]
OUTCOME = {0: "leave unlinked", 1: "curator queue", 2: "assert sameAs"}

QUESTIONS = {
    "link_state": Score(
        instructions="How do the two entity descriptions relate as products?",
        criteria=LEVELS,
    ),
    "same_name": Noul(
        instructions="Do the two entities state the same beer name?",
    ),
    "same_brewery": Noul(
        instructions="Are the two entities from the same brewery?",
    ),
    "same_style": Noul(
        instructions="Do the two entities describe the same beer style?",
    ),
}


@json_cache
def score(pair_id: str) -> dict:
    """One request about one candidate pair -> the score plus the three noul answers."""
    pair = BY_ID[pair_id]
    response = client.system_one(
        state={"entity_a": pair["entity_a"], "entity_b": pair["entity_b"]},
        questions=QUESTIONS,
        model=TYPESAFE_MODEL,
    )
    link = response.answers["link_state"]
    return {
        "score": link.score,
        "probabilities": link.probabilities,
        "confidence": link.confidence,
        "properties": {
            k: response.answers[k].noul for k in QUESTIONS if k != "link_state"
        },
        # tokens and requests are the durable units; don't cache a derived cost
        "input_tokens": response.usage.input_tokens or 0,
        "output_tokens": response.usage.output_tokens or 0,
    }


def route(score_value: float) -> str:
    """The whole decision rule: the nearest level names the outcome."""
    return OUTCOME[min(int(score_value + 0.5), len(LEVELS) - 1)]


def show(pair_id: str) -> None:
    pair, result = BY_ID[pair_id], score(pair_id)
    print(
        f"{pair_id}  score {result['score']:.2f}  confidence {result['confidence']:.2f}"
        f"  ->  {route(result['score'])}"
    )
    for side in ("entity_a", "entity_b"):
        e = pair[side]
        print(f"    {e['name'][:44]:<46}{e['brewery'][:30]:<32}{e['style'][:22]}")
    nouls = result["properties"]
    print(
        f"    name {nouls['same_name']:.2f}   brewery {nouls['same_brewery']:.2f}   "
        f"style {nouls['same_style']:.2f}"
    )

for pair_id in ("c446", "c427", "c100", "c428"):
    show(pair_id)
    print()

c446  score 1.94  confidence 0.92  ->  assert sameAs
    Thomas Hooker Old Marley Barleywine           Thomas Hooker Brewing Company   American Barleywine
    Thomas Hooker Old Marley Barleywine           Thomas Hooker Brewing Company   Barley Wine
    name 0.97   brewery 0.99   style 0.81

c427  score 0.03  confidence 0.95  ->  leave unlinked
    Frost Quake Bourbon Barrel Aged Barley Wine   Wellington County Brewery       American Barleywine
    Lompoc Bourbon Barrel Aged Proletariat Red A  Lompoc Brewing                  Amber Ale
    name 0.02   brewery 0.09   style 0.08

c100  score 1.30  confidence 0.27  ->  curator queue
    Belle Gueule Rousse                           Brasseurs R.J.                  American Amber / Red A
    Belle Gueule Rousse                           Brasseurs RJ                    Amber Lager/Vienna
    name 0.95   brewery 0.94   style 0.35

c428  score 1.10  confidence 0.77  ->  curator queue
    Ambleside Amber Ale                           Bridge Brewing Company          American Amber / Red A
    Bridge Ambleside Amber Ale - Pomegranate & G  Bridge Brewing Company          Amber Ale
    name 0.63   brewery 0.98   style 0.74

# 450 candidate pairs, one request each; a small pool keeps a live run to a few minutes.
with ThreadPoolExecutor(max_workers=MAX_WORKERS) as pool:
    scored = list(pool.map(lambda pair: score(pair["id"]), PAIRS))

scores = [result["score"] for result in scored]
by_outcome: dict[str, list[str]] = {name: [] for name in OUTCOME.values()}
for pair, s in zip(PAIRS, scores):
    by_outcome[route(s)].append(pair["id"])

SURFACE, INK, INK2, MUTED = "#fcfcfb", "#0b0b0b", "#52514e", "#898781"
GRID, AXIS, BLUE, ORANGE = "#e1e0d9", "#c3c2b7", "#2a78d6", "#eb6834"

BINS, TOP = 20, len(LEVELS) - 1
counts = [0] * BINS
for s in scores:
    counts[min(int(s / TOP * BINS), BINS - 1)] += 1
centers = [(i + 0.5) / BINS * TOP for i in range(BINS)]
queued = [c if route(x) == "curator queue" else 0 for c, x in zip(counts, centers)]
settled = [c if route(x) != "curator queue" else 0 for c, x in zip(counts, centers)]

fig, ax = plt.subplots(figsize=(7.2, 3.6), facecolor=SURFACE)
ax.set_facecolor(SURFACE)
for side in ("top", "right"):
    ax.spines[side].set_visible(False)
for side in ("left", "bottom"):
    ax.spines[side].set_color(AXIS)
ax.tick_params(colors=MUTED, labelcolor=INK2, labelsize=9)
ax.set_axisbelow(True)
ax.grid(axis="y", color=GRID, linewidth=0.8)
ax.bar(
    centers, settled, width=TOP / BINS * 0.9, color=BLUE, label="settled automatically"
)
ax.bar(
    centers, queued, width=TOP / BINS * 0.9, color=ORANGE, label="sent to the curator"
)
for edge in (0.5, 1.5):
    ax.axvline(edge, color=INK2, linewidth=1, linestyle="--")
ax.set_xticks([0, 0.5, 1, 1.5, 2])
ax.set_xticklabels(["0\ndifferent", "0.5", "1\nrelated", "1.5", "2\nsame"])
ax.set_xlabel("score for the pair", color=INK2, fontsize=9)
ax.set_ylabel("candidate pairs", color=INK2, fontsize=9)
ax.set_title(
    f"{len(PAIRS)} candidate pairs, scored once each",
    loc="left",
    color=INK,
    fontsize=11,
)
ax.legend(frameon=False, labelcolor=INK2, fontsize=9)
display(fig)
plt.close(fig)

for name in ("assert sameAs", "curator queue", "leave unlinked"):
    n = len(by_outcome[name])
    print(f"{name:<16}{n:>5}  ({n / len(PAIRS):>5.1%})")

assert sameAs      40  ( 8.9%)
curator queue      50  (11.1%)
leave unlinked    360  (80.0%)

playground_link = make_playground_link(
    {"entity_a": BY_ID["c428"]["entity_a"], "entity_b": BY_ID["c428"]["entity_b"]},
    QUESTIONS,
    models=[TYPESAFE_MODEL],
)
display(
    Markdown(
        f"🔗 [Open this pair + questions in the TypeSafe playground]({playground_link})"
    )
)