Triple
T22209460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | F-8 Crusader |
E548901
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object | Vought |
—
|
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: Vought | Statement: [F-8 Crusader, manufacturer, Vought]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vought Context triple: [F-8 Crusader, manufacturer, Vought]
-
A.
Vought
Vought is a surname most notably associated with Russell Vought, an American political figure who served as Director of the U.S. Office of Management and Budget.
-
B.
Vought
chosen
Vought was an American aerospace manufacturer best known for producing military aircraft such as the F4U Corsair.
-
C.
Northrop
Northrop is a major American aerospace and defense company known for designing and producing advanced military aircraft and related technologies.
-
D.
Grumman
Grumman was a major American aerospace and defense company best known for designing and building military and naval aircraft, including several iconic U.S. Navy fighters.
-
E.
Folland Aircraft
Folland Aircraft was a British aircraft manufacturer best known for producing light fighter and trainer aircraft in the post-World War II era.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2aefb881909bddbabd4be0bd58 |
completed | April 28, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:36 p.m.