Triple
T6058246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Taiwan Strait Crisis |
E134966
|
entity |
| Predicate | involvedAgreement |
P68025
|
FINISHED |
| Object | 1958 U.S. decision to escort ROC convoys |
—
|
LITERAL FINISHED |
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: 1958 U.S. decision to escort ROC convoys | Statement: [Second Taiwan Strait Crisis, involvedAgreement, 1958 U.S. decision to escort ROC convoys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedAgreement Context triple: [Second Taiwan Strait Crisis, involvedAgreement, 1958 U.S. decision to escort ROC convoys]
-
A.
agreement
Indicates that two or more parties mutually consent to and accept shared terms, conditions, or understandings.
-
B.
agreementInvoked
Indicates that a formal agreement or contract has been activated, called upon, or put into effect between the related entities.
-
C.
aimOfAgreement
Indicates the intended purpose or objective that an agreement is designed to achieve.
-
D.
basedOnAgreementWith
Indicates that something exists, is done, or is determined on the basis of a prior agreement or accord between the involved parties.
-
E.
legalDocumentInvolvement
Indicates that an entity is involved with a legal document in some specified role (e.g., author, signer, subject, or recipient).
- F. None of above. chosen
Provenance (4 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_69c00877b6d4819096b0e163728b73a3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0570e64408190ae7a2504f63bb58a |
completed | March 22, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69c049edc6f0819092ca620d9073ad26 |
completed | March 22, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69c04dbefd1081909795fe1a812b991a |
completed | March 22, 2026, 8:14 p.m. |
Created at: March 22, 2026, 4:10 p.m.