Triple
T23555737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angel |
E578181
|
entity |
| Predicate | closeAlly |
P14992
|
FINISHED |
| Object | Iceman |
—
|
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 | Statement: [Angel, closeAlly, Iceman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iceman Context triple: [Angel, closeAlly, Iceman]
-
A.
Iceman
Iceman is the nickname of Adam Vinatieri, the legendary NFL placekicker renowned for his clutch, game-winning field goals under extreme pressure.
-
B.
Iceman
Iceman is a 1984 science fiction drama film about the discovery and revival of a prehistoric man frozen in ice.
-
C.
Iceman
Iceman is the call sign of Tom Kazansky, a skilled and competitive U.S. Navy fighter pilot from the "Top Gun" film series.
-
D.
Iceman
chosen
Iceman is a founding member of the X-Men with the mutant ability to generate and control ice and cold.
-
E.
Iceman
Iceman is a 2014 Hong Kong action-comedy film starring Donnie Yen as a Ming Dynasty warrior who time-travels to modern-day Hong Kong.
- 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_69e245fa93448190919cb04534560542 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1aed37f248190992f040f4d22f0bf |
completed | April 29, 2026, 7:10 a.m. |
Created at: April 17, 2026, 6:12 p.m.