Triple
T22282696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sundown Trail |
E550773
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Tom London |
—
|
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: Tom London | Statement: [Sundown Trail, hasCastMember, Tom London]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom London Context triple: [Sundown Trail, hasCastMember, Tom London]
-
A.
Tom London
chosen
Tom London was a prolific American character actor best known for his numerous roles in Western films and serials during the early to mid-20th century.
-
B.
Michael Jameson
Michael Jameson is the husband of Mireille Duval Jameson, known primarily in relation to her.
-
C.
Michael Thornhill
Michael Thornhill was an Australian film director and screenwriter known for his work in the 1970s New Wave cinema movement.
-
D.
Matthew Drake
Matthew Drake is known primarily as the husband of American actress Arlene Martel.
-
E.
John Knight
John Knight was an American newspaper editor and publisher best known for his influential leadership in 20th-century U.S. journalism and for founding the media company that became Knight Ridder.
- 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_69e11e44d538819097c6b8f333af3352 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14eacd6cc8190812c6f672641050e |
completed | April 29, 2026, 12:19 a.m. |
Created at: April 16, 2026, 8:40 p.m.