Triple
T27871916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Order Star Destroyer |
E704811
|
entity |
| Predicate | hangarComplement |
P163245
|
FINISHED |
| Object | shuttles |
—
|
LITERAL FINISHED |
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: shuttles | Statement: [First Order Star Destroyer, hangarComplement, shuttles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hangarComplement Context triple: [First Order Star Destroyer, hangarComplement, shuttles]
-
A.
hangarComplement
chosen
Indicates that one entity serves as the hangar-based complement or support unit for another, typically housing, servicing, or supporting it within a hangar facility.
-
B.
hasHangars
Indicates that one entity possesses or contains hangars used for housing aircraft or similar vehicles.
-
C.
hasHangarCount
Indicates the number of hangars associated with or contained by an entity.
-
D.
hardpoints
Indicates a relationship where one entity provides designated attachment locations or mounting interfaces on its structure for connecting other components or equipment.
-
E.
airGroupComplement
Indicates that one air group serves as a complement or supporting component to another air group within a larger operational structure.
- 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_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6895f0819088655277e45859a8 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 6:25 p.m.