Triple
T17420873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hatchet II |
E423610
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Sarah Elbert |
—
|
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: Sarah Elbert | Statement: [Hatchet II, producer, Sarah Elbert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Elbert Context triple: [Hatchet II, producer, Sarah Elbert]
-
A.
Sarah Elbert
chosen
Sarah Elbert is a film producer best known for her work on the horror movie "Hatchet."
-
B.
Lisa Gottsegen
Lisa Gottsegen is an American businesswoman and philanthropist best known as the longtime wife of actor Dustin Hoffman.
-
C.
Sarah Bolger
Sarah Bolger is an Irish actress known for her roles in films like "In America" and "The Spiderwick Chronicles" and TV series such as "The Tudors" and "Once Upon a Time."
-
D.
Sarah Ulmer
Sarah Ulmer is a New Zealand former track cyclist and Olympic gold medallist renowned for breaking the individual pursuit world record.
-
E.
Sarah Roemer
Sarah Roemer is an American actress and former model best known for her role in the thriller film "Disturbia" and appearances in various television series and movies.
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e442372954819085f332efc7067ae9 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.