Triple
T7809477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hot Water |
E180640
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Tim Whelan |
E525577
|
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: Tim Whelan | Statement: [Hot Water, screenwriter, Tim Whelan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tim Whelan Context triple: [Hot Water, screenwriter, Tim Whelan]
-
A.
Tim Whelan
chosen
Tim Whelan was a British film director and screenwriter known for his work in early Hollywood and British cinema, including comedies and adventure films in the 1930s and 1940s.
-
B.
Gary Whelan
Gary Whelan is an English drummer best known for his work with the influential Madchester band Happy Mondays.
-
C.
Michael Whelan
Michael Whelan is an acclaimed American artist best known for his influential science fiction and fantasy book and album cover illustrations.
-
D.
Patrick Doherty
Patrick Doherty was one of the unarmed civil rights marchers shot and killed by British soldiers during the Bloody Sunday massacre in Derry, Northern Ireland, in 1972.
-
E.
Kevin Corrigan
Kevin Corrigan is an American character actor known for his offbeat, often darkly comic supporting roles in numerous independent films and major studio movies.
- 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_69ca827f6f148190beca4e245b993506 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf78bb4b08190b2b3b51c5a0a033c |
completed | March 30, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccec40f5e88190bc0fbb4ad99d09c6 |
completed | April 1, 2026, 9:58 a.m. |
Created at: March 30, 2026, 4:36 p.m.