Triple
T3376711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iron Man 3 |
E71082
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Kevin Feige |
E199353
|
NE 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: Kevin Feige | Statement: [Iron Man 3, producer, Kevin Feige]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Feige Context triple: [Iron Man 3, producer, Kevin Feige]
-
A.
Kevin Feige
chosen
Kevin Feige is an American film producer best known as the president of Marvel Studios and the chief architect of the Marvel Cinematic Universe.
-
B.
Peter Hunt
Peter Hunt is a British film editor and director best known for his work on the early James Bond films, including directing "On Her Majesty's Secret Service."
-
C.
David Heyman
David Heyman is a British film producer best known for originating and producing the Harry Potter film series and other major studio franchises.
-
D.
Simon Kinberg
Simon Kinberg is a British-born American screenwriter and producer best known for his extensive work on the X-Men film franchise and other major Hollywood blockbusters.
-
E.
Steve Golin
Steve Golin was an American film and television producer and founder of the production company Anonymous Content, known for backing acclaimed projects such as "Spotlight," "Eternal Sunshine of the Spotless Mind," and numerous award-winning TV series.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2e776508190bc123fb17b36f062 |
completed | March 8, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b334465b50819080c6f23eaa6583be |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:13 p.m.