Triple
T25393694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhao Ziyang |
E636233
|
entity |
| Predicate | mentorOrKeyAlly |
P32710
|
FINISHED |
| Object | Deng Xiaoping |
—
|
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: Deng Xiaoping | Statement: [Zhao Ziyang, mentorOrKeyAlly, Deng Xiaoping]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentorOrKeyAlly Context triple: [Zhao Ziyang, mentorOrKeyAlly, Deng Xiaoping]
-
A.
mentorOrPartner
chosen
Indicates a relationship in which one entity either provides guidance and support to another as a mentor or collaborates with them on relatively equal footing as a partner.
-
B.
mentorCharacter
Indicates that one character serves as a mentor, providing guidance, teaching, or support to another character.
-
C.
trainingPartner
Indicates that two entities participate together in training activities, typically collaborating or assisting each other in practice or skill development.
-
D.
advisorOf
Indicates that one entity serves as an advisor, providing guidance or counsel, to another entity.
-
E.
partnerInLeadershipWith
Indicates that two entities share a joint leadership role or responsibility, collaborating as partners in guiding or managing an organization, group, or initiative.
- 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_69e75db263888190b77fff9e2827b9a2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f56572b9288190abaf921c761fd843 |
completed | May 2, 2026, 2:46 a.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:49 p.m.