Triple
T29574493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing Coup |
E753404
|
entity |
| Predicate | involvedWarlord |
P109086
|
FINISHED |
| Object | Feng Yuxiang |
—
|
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: Feng Yuxiang | Statement: [Beijing Coup, involvedWarlord, Feng Yuxiang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedWarlord Context triple: [Beijing Coup, involvedWarlord, Feng Yuxiang]
-
A.
warlordCharacter
chosen
Indicates that one entity plays the role or has the characteristics of a warlord in relation to another entity or within a given context.
-
B.
producedWarlord
Indicates that an entity is responsible for bringing about, creating, or giving rise to a particular warlord.
-
C.
associatedWithWar
Indicates a relationship where an entity is connected or related to war, such as by involvement, influence, cause, or context.
-
D.
preeminentWarlordLineage
Indicates that one entity descends from or belongs to a lineage recognized as the foremost or most dominant among warlords.
-
E.
wargBond
Indicates a special bond or partnership between a warg and another entity, typically involving loyalty, cooperation, or shared purpose.
- 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_69f0ef7fcb4881908a933110adb9bda1 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: April 28, 2026, 6:01 p.m.