Triple
T20558353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harriet (2019 film) |
E504778
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Wyatt Smith |
—
|
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: Wyatt Smith | Statement: [Harriet (2019 film), editedBy, Wyatt Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wyatt Smith Context triple: [Harriet (2019 film), editedBy, Wyatt Smith]
-
A.
Wyatt Smith
Wyatt Smith is an American actor best known for his role in the mixed martial arts drama film "Never Back Down."
-
B.
Wyatt Smith
chosen
Wyatt Smith is an American film editor known for his work on major studio productions, including musical and fantasy films.
-
C.
Wyatt Jones
Wyatt Jones is an editor known for his work on the publication titled "Immortals."
-
D.
Wyatt McLean
Wyatt McLean is the son of American singer-songwriter Don McLean, best known for the classic song "American Pie."
-
E.
Wyatt Cenac
Wyatt Cenac is an American comedian, writer, and actor best known for his work as a correspondent on The Daily Show and for creating and starring in the HBO series "Wyatt Cenac's Problem Areas."
- 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a5df84088190848c7eb35564d8f9 |
completed | April 20, 2026, 10:17 p.m. |
Created at: April 16, 2026, 11:38 a.m.