Triple
T24405446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragon Gate USA |
E615297
|
entity |
| Predicate | featuredTalentFrom |
P101209
|
FINISHED |
| Object | Dragon Gate |
—
|
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: Dragon Gate | Statement: [Dragon Gate USA, featuredTalentFrom, Dragon Gate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredTalentFrom Context triple: [Dragon Gate USA, featuredTalentFrom, Dragon Gate]
-
A.
discoversTalentOf
Indicates that one entity identifies or recognizes the talent or abilities possessed by another entity.
-
B.
featuredFor
chosen
Indicates that one entity is highlighted, promoted, or specially showcased in the context or for the benefit of another entity.
-
C.
featuredDancers
Indicates that certain dancers are highlighted or given special prominence in a performance, event, or context.
-
D.
renduCélèbrePar
Indicates that one entity became famous or well-known as a result of the actions, influence, or association of another entity.
-
E.
featuresVariousArtists
Indicates that something (typically a creative work) includes contributions from multiple distinct artists rather than a single primary artist.
- 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_69e2d7e780bc81908049c779e697a7f6 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f294de76848190bd2cf3c7add2dcf1 |
completed | April 29, 2026, 11:31 p.m. |
| PD | Predicate disambiguation | batch_69f287c4a2b48190b80fb7a3c0e9b018 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:05 a.m.