Triple
T21150192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 倪桂珍 |
E521166
|
entity |
| Predicate | 对宋子文的影响 |
P63153
|
FINISHED |
| Object | 在成长与教育方面具有重要影响 |
—
|
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: 在成长与教育方面具有重要影响 | Statement: [倪桂珍, 对宋子文的影响, 在成长与教育方面具有重要影响]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 对宋子文的影响 Context triple: [倪桂珍, 对宋子文的影响, 在成长与教育方面具有重要影响]
-
A.
業績の影響
Indicates that one entity’s performance or results have an effect on, or bring about changes in, another entity or outcome.
-
B.
hasSignificantInfluenceIn
chosen
Indicates that one entity exerts a substantial impact or shaping effect on another entity within a particular domain, context, or outcome.
-
C.
hasLoanInfluenceFrom
Indicates that one entity’s loan terms, availability, or conditions are affected or shaped by another entity.
-
D.
hadInfluenceOn
Indicates that one entity affected, shaped, or contributed to the development, behavior, or characteristics of another entity.
-
E.
influencedPerson
Indicates that one entity has affected, shaped, or guided the thoughts, behavior, or development of another person.
- 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_69e0b50c6a848190a4e525a77a319b8a |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72400911c8190978e88138a9bfaff |
completed | April 21, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69e5f5f8a5bc819081918c7fa8e4496d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 2:58 p.m.