Triple
T14080643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Arquette |
E338855
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Scream |
E136030
|
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: Scream | Statement: [David Arquette, notableWork, Scream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scream Context triple: [David Arquette, notableWork, Scream]
-
A.
Scream
Scream is a 2009 studio album by American rock musician Chris Cornell that explores a more pop and electronic-influenced sound produced in collaboration with Timbaland.
-
B.
Scream
"Scream" is a song by American rock band Long Gone, known for its intense energy and emotionally charged sound.
-
C.
Scream
chosen
Scream is a 1996 American slasher film directed by Wes Craven that revitalized the horror genre with its self-aware, meta-commentary on slasher movie tropes.
-
D.
Scream
"Scream" is an energetic dance-pop and R&B single by Usher known for its club-ready production and catchy, upbeat hook.
-
E.
Scream
Scream is a high-thrill drop tower ride located at the Six Flags Fiesta Texas amusement park.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb672c08081908e1ff9030745776a |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.