Triple
T17565078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Val Kilmer |
E427788
|
entity |
| Predicate | notableRole |
P22
|
FINISHED |
| Object | Iceman in Top Gun |
—
|
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: Iceman in Top Gun | Statement: [Val Kilmer, notableRole, Iceman in Top Gun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iceman in Top Gun Context triple: [Val Kilmer, notableRole, Iceman in Top Gun]
-
A.
Top Gun
Top Gun is a 1955 American Western film starring Sterling Hayden as a notorious gunslinger who returns to his hometown to warn of an impending outlaw attack.
-
B.
Top Gun
chosen
Top Gun is a 1986 American action drama film starring Tom Cruise as a hotshot Navy fighter pilot, renowned for its high-octane aerial sequences, iconic soundtrack, and lasting impact on pop culture.
-
C.
Ace the Skyhawk
Ace the Skyhawk is the costumed hawk mascot representing Stonehill College at its athletic events and campus activities.
-
D.
Ace the Warhawk
Ace the Warhawk is the costumed bird mascot representing the University of Louisiana at Monroe’s athletic teams and school spirit.
-
E.
SkyHawk
SkyHawk is Seagate’s specialized line of hard disk drives designed for surveillance systems, optimized for continuous 24/7 video recording and high reliability.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592ce42c8190a54a0a328c5e8ffc |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.