Triple
T15211199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clemency |
E363517
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Wendell Pierce |
E32638
|
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: Wendell Pierce | Statement: [Clemency, starring, Wendell Pierce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wendell Pierce Context triple: [Clemency, starring, Wendell Pierce]
-
A.
Wendell Pierce
chosen
Wendell Pierce is an American actor best known for his roles in acclaimed television series such as "The Wire," "Treme," and "Suits."
-
B.
Jesse L. Martin
Jesse L. Martin is an American actor and singer best known for his roles as Detective Ed Green on "Law & Order" and Tom Collins in the original Broadway production of "Rent."
-
C.
Ennis Howard Plemons
Ennis Howard Plemons is the son of American actors Kirsten Dunst and Jesse Plemons.
-
D.
Titus Welliver
Titus Welliver is an American actor best known for his roles in the television series "Bosch" and "Deadwood," as well as numerous film and TV character roles.
-
E.
Mark Pellington
Mark Pellington is an American film and music video director known for his visually striking, emotionally intense work on projects such as U2’s “One” and the film “Arlington Road.”
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0076ad4ec81908d36f541fca08d72 |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed33f9abc8190bf8166c1fd9fcac6 |
completed | May 9, 2026, 6:25 a.m. |
Created at: April 10, 2026, 3:11 a.m.