Triple
T27872288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starfighter Corps |
E704820
|
entity |
| Predicate | usesStarfighterModel |
P80075
|
FINISHED |
| Object | T-70 X-wing starfighter |
—
|
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: T-70 X-wing starfighter | Statement: [Starfighter Corps, usesStarfighterModel, T-70 X-wing starfighter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesStarfighterModel Context triple: [Starfighter Corps, usesStarfighterModel, T-70 X-wing starfighter]
-
A.
usesStarfighter
chosen
Indicates that one entity operates or employs a starfighter as its vehicle, tool, or means of transportation or combat.
-
B.
notableStarfighter
Indicates that an entity is a starfighter recognized for particular significance, prominence, or distinction (e.g., historically, tactically, or culturally).
-
C.
usesStarshipClass
Indicates that an entity operates, employs, or is associated with a particular class or type of starship.
-
D.
hasStarship
Indicates that one entity possesses, controls, or is associated with a particular starship.
-
E.
hasStarshipClassDepicted
Indicates that an entity includes or shows a depiction of a particular starship class.
- 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_69ef84111bb4819084298f994b31c62f |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 27, 2026, 6:25 p.m.