Triple
T22546142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiss of Death |
E557433
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Coleen Gray |
—
|
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: Coleen Gray | Statement: [Kiss of Death, starring, Coleen Gray]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coleen Gray Context triple: [Kiss of Death, starring, Coleen Gray]
-
A.
Coleen Gray
chosen
Coleen Gray was an American film and television actress best known for her roles in classic 1940s and 1950s noir and Western films.
-
B.
Coleen Sexton
Coleen Sexton is an American stage actress and singer best known for her work in musical theatre, including prominent roles in Broadway and touring productions.
-
C.
Colleen McCool
Colleen McCool is a notable individual recognized as a bearer of the surname McCool.
-
D.
Colleen Collette
Colleen Collette is one of the teenage convenience-store-clerk protagonists in Kevin Smith’s horror-comedy film "Yoga Hosers."
-
E.
Laura Regan
Laura Regan is a Canadian actress known for her roles in science fiction and horror projects, including playing a key character in the television adaptation of "Minority Report."
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f35b9888190b4e1b50d5097b211 |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.