Triple
T32689106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marquis of Huan |
E835806
|
entity |
| Predicate | posthumouslyConferredOn |
P18219
|
FINISHED |
| Object | Zhang Fei |
—
|
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: Zhang Fei | Statement: [Marquis of Huan, posthumouslyConferredOn, Zhang Fei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: posthumouslyConferredOn Context triple: [Marquis of Huan, posthumouslyConferredOn, Zhang Fei]
-
A.
posthumousRecognitionBy
Indicates that an entity receives recognition, honor, or acknowledgment from another entity after the former has died.
-
B.
yearOfPosthumousAward
Indicates the calendar year in which an award was conferred after the recipient’s death.
-
C.
posthumousTitleYear
Indicates the year in which an entity was formally granted a title or honor after its death.
-
D.
conferredOn
chosen
Indicates that something (such as an honor, title, degree, or benefit) has been formally granted or bestowed upon a particular entity.
-
E.
posthumousAwardsRestoredInYear
Indicates that awards, previously revoked or unrecognized during a person’s lifetime, were officially reinstated or granted in a specified year after their death.
- 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_69f3493211388190993801216afbc2a7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:09 a.m.