Triple
T17037336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Trachtenberg |
E413354
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Prey |
E270957
|
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: Prey | Statement: [Dan Trachtenberg, notableWork, Prey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prey Context triple: [Dan Trachtenberg, notableWork, Prey]
-
A.
Prey
Prey is a British television crime drama series starring John Simm as a detective on the run while trying to clear his name.
-
B.
Prey
Prey is a techno-thriller novel by Michael Crichton that explores the dangers of advanced nanotechnology and artificial intelligence run amok.
-
C.
Prey (2017 video game)
chosen
Prey (2017 video game) is a science fiction first-person action-adventure game set on a space station overrun by shape-shifting aliens, known for its immersive sim design and player freedom.
-
D.
"Prey"
"Prey" is an episode of Star Trek: Voyager that centers on the Hirogen hunters' pursuit of a Species 8472 individual aboard the starship.
-
E.
Predators
Predators is the short name of the Orlando Predators, a professional arena football team based in Orlando, Florida.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f38b58819093af4054c3459726 |
completed | April 18, 2026, 7:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b5b71f48190b6c865d57668b5d1 |
completed | May 10, 2026, 11:57 p.m. |
Created at: April 10, 2026, 5:33 a.m.