Triple
T20819791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Legion (2010 film) |
E512542
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Scott Stewart |
—
|
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: Scott Stewart | Statement: [Legion (2010 film), writer, Scott Stewart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scott Stewart Context triple: [Legion (2010 film), writer, Scott Stewart]
-
A.
Scott Stewart
chosen
Scott Stewart is an American filmmaker and visual effects artist best known for directing supernatural action films such as "Legion" (2010).
-
B.
Dan Stewart
Dan Stewart is known primarily as the husband of former Australian Test cricket captain Kim Hughes.
-
C.
Jon Randall Stewart
Jon Randall Stewart is an American country music singer, songwriter, and producer known for his work both as a solo artist and as a collaborator with prominent Nashville acts.
-
D.
Todd Stewart
Todd Stewart is a collegiate sports administrator best known for serving as the athletic director at Western Kentucky University.
-
E.
Brad Stewart
Brad Stewart is an American bassist best known for his work with the rock band Shinedown.
- 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_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f6a65481909a0df78616e185e4 |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.