Triple
T28204217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orphans |
E716968
|
entity |
| Predicate | notableActorInRolePhillip |
P190393
|
FINISHED |
| Object | Kevin Anderson |
—
|
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: Kevin Anderson | Statement: [Orphans, notableActorInRolePhillip, Kevin Anderson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableActorInRolePhillip Context triple: [Orphans, notableActorInRolePhillip, Kevin Anderson]
-
A.
notableCastMember
Indicates that an entity is a member of the cast of another entity (such as a film, show, or production) and is considered particularly notable or significant in that role.
-
B.
portraysNotableAct
Indicates that an entity depicts or represents a significant or noteworthy action performed by another entity.
-
C.
leadActorForCharacter Philip Adams
chosen
Indicates that the specified person is the primary actor portraying the character Philip Adams.
-
D.
notableStarName
Indicates that the subject is known by the specified star name as a notable or prominent designation.
-
E.
notableBearActor
Indicates that the subject is a bear who is recognized for acting roles or performances.
- 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_69efd6b826908190857e6e7dad74ed93 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a00a22e32f481909b6006c5b1cdefd3 |
completed | May 10, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_6a00a1bd9c908190b4aa17a61f48126f |
completed | May 10, 2026, 3:18 p.m. |
Created at: April 27, 2026, 10:34 p.m.