Triple
T20661930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Finders Keepers |
E507778
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Holly Gibney |
—
|
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: Holly Gibney | Statement: [Finders Keepers, mainCharacter, Holly Gibney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holly Gibney Context triple: [Finders Keepers, mainCharacter, Holly Gibney]
-
A.
Holly Gibney
chosen
Holly Gibney is a socially anxious but brilliant and determined private investigator created by Stephen King, who appears across multiple novels including the Bill Hodges trilogy and The Outsider.
-
B.
Noelle Lippman
Noelle Lippman is an American actress and former model best known for being married to television producer Dick Wolf.
-
C.
Jennifer Naughton
Jennifer Naughton is a local political leader who serves as the mayor of Spring Lake, New Jersey.
-
D.
Sarah Greene
Sarah Greene is an Irish actress known for her work in film, television, and theatre, including acclaimed performances in projects such as "Penny Dreadful" and "Dublin Murders."
-
E.
Jane Bingum
Jane Bingum is the intelligent, plus-sized lawyer protagonist of the television series "Drop Dead Diva," known for combining sharp legal skills with a compassionate, quirky personality.
- 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_69e0b4c059bc81908ea762cd73ea4424 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6b2f2ee4081908df9ba897c9dfc98 |
completed | April 20, 2026, 11:12 p.m. |
Created at: April 16, 2026, 11:44 a.m.