Triple
T15063816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pet Sematary II |
E379703
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Darlanne Fluegel |
—
|
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: Darlanne Fluegel | Statement: [Pet Sematary II, stars, Darlanne Fluegel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Darlanne Fluegel Context triple: [Pet Sematary II, stars, Darlanne Fluegel]
-
A.
Darlanne Fluegel
chosen
Darlanne Fluegel was an American actress and model known for her roles in 1980s films and television, including prominent appearances in crime and action genres.
-
B.
Nicole Flender
Nicole Flender is an American real estate broker and former Broadway dancer best known as the mother of actor Timothée Chalamet.
-
C.
Alyson Fouse
Alyson Fouse is an American television and film writer known for her work on comedy projects including the parody film "Scary Movie 2."
-
D.
Lianne Neudecker
Lianne Neudecker is a character associated with Hammad, likely appearing in the same narrative or production as a supporting or related figure.
-
E.
Lisa Gottsegen
Lisa Gottsegen is an American businesswoman and philanthropist best known as the longtime wife of actor Dustin Hoffman.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee803ac81908bb7d66e49c2eb72 |
completed | April 15, 2026, 12:42 a.m. |
Created at: April 10, 2026, 3:02 a.m.