Triple
T37669342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gwen DeMarco |
E937910
|
entity |
| Predicate | worksAsCharacterOnShow |
P191743
|
FINISHED |
| Object | Lt. Tawny Madison |
—
|
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: Lt. Tawny Madison | Statement: [Gwen DeMarco, worksAsCharacterOnShow, Lt. Tawny Madison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksAsCharacterOnShow Context triple: [Gwen DeMarco, worksAsCharacterOnShow, Lt. Tawny Madison]
-
A.
worksForCharacterPlayedBy
Indicates that one character is employed by, or works under, another character who is portrayed by a specific actor.
-
B.
playsForCharacters
chosen
Indicates that an entity performs or portrays specific characters, typically in a work such as a film, show, or game.
-
C.
appearsWithCharacter
Indicates that two characters are shown or present together within the same scene, shot, or context.
-
D.
worksOnTVShow
Indicates that an individual is professionally involved in the production or creation of a particular television show.
-
E.
worksWithFictionalCharacter
Indicates that one entity collaborates or interacts in a work-related context with another entity that is a fictional character.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
Created at: May 3, 2026, 4:18 p.m.