Triple
T28343670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Taizong Wen Huangdi |
E717887
|
entity |
| Predicate | appliedAfterDeathOf |
P191884
|
FINISHED |
| Object | Hong Taiji |
—
|
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: Hong Taiji | Statement: [Emperor Taizong Wen Huangdi, appliedAfterDeathOf, Hong Taiji]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedAfterDeathOf Context triple: [Emperor Taizong Wen Huangdi, appliedAfterDeathOf, Hong Taiji]
-
A.
afterDeathOf
Indicates that one event, state, or condition occurs subsequent to and as a result of the death of a specified entity.
-
B.
completionAfterDeathOf
Indicates that one event, process, or work is completed only after the death of a specified person.
-
C.
afterDeath
Indicates that one event, state, or condition occurs subsequent to and as a result of an entity’s death.
-
D.
releasedAfterDeathOf
Indicates that something (such as a work, product, or announcement) was released only after the death of a specified person.
-
E.
continuedAfterDeathOf
Indicates that an action, state, or process persisted beyond and despite the death of a specified entity.
- 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_69eff6eb30388190b898b96c4be6f49d |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69fcef636dfc819085cf91323f2e4edd |
completed | May 7, 2026, 8 p.m. |
Created at: April 28, 2026, 12:41 a.m.