Triple
T8032731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Extras |
E187025
|
entity |
| Predicate | leadActorPlaysCharacter |
P42172
|
FINISHED |
| Object | Ricky Gervais as Andy Millman |
—
|
LITERAL 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: Ricky Gervais as Andy Millman | Statement: [Extras, leadActorPlaysCharacter, Ricky Gervais as Andy Millman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadActorPlaysCharacter Context triple: [Extras, leadActorPlaysCharacter, Ricky Gervais as Andy Millman]
-
A.
roleInFamousPlay
Indicates that an entity portrays or has portrayed a specific character in a well-known theatrical play.
-
B.
playedBy
Indicates that a role, character, or performance is portrayed or executed by a specific person or agent.
-
C.
actorRole
Indicates that an entity participates in an event or action in a specific capacity or function (such as performer, initiator, or responsible party).
-
D.
characterPortrayedIs
Indicates that one entity serves as the fictional or dramatic role that is depicted or played by another entity.
-
E.
playsInRole
chosen
Indicates that an entity performs or appears in a specific role within a production, event, or context.
- F. None of above.
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_69ca82ae2d1081909dbfee42b41db419 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ef18da48190835454a5eb969da7 |
completed | March 31, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69cb049688208190b32088bd2c5930bc |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:22 p.m.