Triple
T2305514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coquette (1929 film) |
E51829
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | William Janney |
E248170
|
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: William Janney | Statement: [Coquette (1929 film), hasCastMember, William Janney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Janney Context triple: [Coquette (1929 film), hasCastMember, William Janney]
-
A.
William Janney
chosen
William Janney was an American film actor active in the late 1920s and 1930s, known for his roles in early sound-era dramas and adventure films.
-
B.
William Jackson
William Jackson was an American soldier and statesman best known for serving as the secretary to the 1787 United States Constitutional Convention.
-
C.
James Lick Robnett
James Lick Robnett is an individual whose personal name is associated with the surname Robnett.
-
D.
John Neely Bryan
John Neely Bryan was an American trader and lawyer best known as the founder of the city of Dallas, Texas.
-
E.
William H. Kirkland
William H. Kirkland was the husband of actress and vaudeville performer June Havoc.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc60300388190993bed7d312a92d5 |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1f78cce88190a74f9ab6a540fe83 |
completed | March 9, 2026, 7:28 p.m. |
Created at: March 4, 2026, 7:49 p.m.