Triple
T9565600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mank |
E230780
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Tom Pelphrey |
E780745
|
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: Tom Pelphrey | Statement: [Mank, castMember, Tom Pelphrey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Pelphrey Context triple: [Mank, castMember, Tom Pelphrey]
-
A.
Tom Pelphrey
chosen
Tom Pelphrey is an American actor known for his roles in television series such as "Ozark," "Iron Fist," and "Guiding Light."
-
B.
Jeff Pehrson
Jeff Pehrson is an American singer-songwriter and harmony vocalist best known for his work with post-Grateful Dead band Furthur and the folk-rock duo Box Set.
-
C.
Jerry Perenchio
Jerry Perenchio was an American entertainment executive and billionaire who built his fortune through talent management, film and television production, and ownership of Univision.
-
D.
Mike Malloy
Mike Malloy is a progressive American radio talk show host known for his outspoken, left-leaning political commentary and work on various liberal talk radio networks.
-
E.
Keith Poulson
Keith Poulson is an American actor known for his work in independent films and for roles in offbeat, character-driven 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_69ca847f22188190a56e4a97625bef22 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd996c0a1081908a8356c454e60f74 |
completed | April 1, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d152abb0788190ab2e204d9a082ccf |
completed | April 4, 2026, 6:04 p.m. |
Created at: March 30, 2026, 8:04 p.m.