Triple
T10201323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seed of Chucky |
E238888
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Corey Sienega |
E678662
|
NE 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: Corey Sienega | Statement: [Seed of Chucky, producer, Corey Sienega]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Corey Sienega Context triple: [Seed of Chucky, producer, Corey Sienega]
-
A.
Corey Sienega
chosen
Corey Sienega is a film producer best known for her work on genre and independent movies, including the psychological horror-thriller "Frailty."
-
B.
Corey Gaines
Corey Gaines is an American basketball coach and former player best known for leading the WNBA’s Phoenix Mercury to a championship as head coach.
-
C.
Corey Britz
Corey Britz is an American bassist and musician best known for playing with the British rock band Bush.
-
D.
Corey Palent
Corey Palent is a television producer best known for serving as an executive producer of the daytime talk program "The Jennifer Hudson Show."
-
E.
Corey Hill
Corey Hill is a residential neighborhood in Brookline, Massachusetts, known for its steep hillside setting and views overlooking Boston.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84e1ea088190b38162e43d4cfa8f |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdee40cb7481908a1bf4d5636eb8ef |
completed | April 2, 2026, 4:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f6e73a2881908563e9e6a02df944 |
completed | April 9, 2026, 12:46 a.m. |
Created at: March 30, 2026, 9:14 p.m.