Triple
T23881333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 辛丑条约 |
E600207
|
entity |
| Predicate | 缔约中国代表 |
P63848
|
FINISHED |
| Object | 庆亲王奕劻 |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 庆亲王奕劻 | Statement: [辛丑条约, 缔约中国代表, 庆亲王奕劻]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 缔约中国代表 Context triple: [辛丑条约, 缔约中国代表, 庆亲王奕劻]
-
A.
wasSignatoryOf
chosen
Indicates that an entity formally signed or endorsed a specific document, agreement, or treaty as a participating party.
-
B.
signatoryGovernment
Indicates that a government is a formal signer or ratifying party to an agreement, treaty, or similar binding instrument.
-
C.
signatoryMinister
Indicates that a minister has formally signed or endorsed a document, agreement, or treaty as an official signatory.
-
D.
representativeInCountry
Indicates that one entity serves as an official representative or agent of another entity within a specified country.
-
E.
seatOfPlenipotentiaryRepresentative
Indicates the location or institution that serves as the official base or office for a plenipotentiary representative.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e295318e148190b9979d8fc02e168f |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cc05e4d48190864fc47bdffa4ca9 |
completed | April 29, 2026, 9:14 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:24 p.m.