Triple
T9790319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Haunted House |
E237588
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Dave Sheridan |
E566910
|
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: Dave Sheridan | Statement: [A Haunted House, starring, Dave Sheridan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dave Sheridan Context triple: [A Haunted House, starring, Dave Sheridan]
-
A.
Dave Sheridan
chosen
Dave Sheridan is an American actor and comedian best known for his role as the bumbling Officer Doofy in the parody film "Scary Movie."
-
B.
Scott Sherwood
Scott Sherwood is a charming yet scheming station manager character from the 1990s AMC television series "Remember WENN."
-
C.
Chris Sheridan
Chris Sheridan is an American television writer and producer best known for his long-running work on the animated series "Family Guy."
-
D.
Greg Shephard
Greg Shephard is a television producer best known for his executive production work on the true-crime drama series "The Act."
-
E.
Matthew Shafer
Matthew Shafer is an American writer known for his work on the animated series "Cowboy Bebop" and related projects.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda215b3108190a897552e1dc91cc4 |
completed | April 1, 2026, 10:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5abb26c81909d597b65f24f9bcf |
completed | April 5, 2026, 3:23 a.m. |
Created at: March 30, 2026, 8:28 p.m.