Triple
T3286258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Keaton |
E68988
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Spotlight |
E238253
|
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: Spotlight | Statement: [Michael Keaton, notableWork, Spotlight]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Spotlight Context triple: [Michael Keaton, notableWork, Spotlight]
-
A.
Spotlight
"Spotlight" is an R&B ballad by Jennifer Hudson that showcases her powerful vocals and explores themes of control and emotional struggle in a relationship.
-
B.
Spotlight
chosen
"Spotlight" is an Academy Award–winning investigative drama film about The Boston Globe's uncovering of widespread child abuse within the Catholic Church.
-
C.
Spotlight
Spotlight is Snapchat’s short-form video platform that showcases user-generated content in a TikTok-style, vertically scrolling feed.
-
D.
Spotlight
Spotlight is a curated program within the New York Film Festival that showcases notable new films, special screenings, and high-profile premieres outside the main competition.
-
E.
Spotlight
Spotlight is Apple’s system-wide search feature on macOS and iOS that quickly locates files, apps, and information across a device and the web.
- 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_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb05779d08190a5517951e71b1380 |
completed | March 8, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e85b6a1081908581b2040b8ce261 |
completed | March 12, 2026, 4:22 p.m. |
Created at: March 8, 2026, 3:10 p.m.