Triple
T15031158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Pinkney |
E378346
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Bill Pinkney |
E378346
|
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: Bill Pinkney | Statement: [Bill Pinkney, name, Bill Pinkney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Pinkney Context triple: [Bill Pinkney, name, Bill Pinkney]
-
A.
Bill Pinkney
chosen
Bill Pinkney was an American R&B singer best known as an original member and longtime lead of the vocal group The Drifters.
-
B.
Pamela Gray
Pamela Gray is an American screenwriter known for her work on character-driven drama films, including the military biographical film "Megan Leavey."
-
C.
Christian Robinson
Christian Robinson is an acclaimed American illustrator and author known for his distinctive, colorful artwork in numerous award-winning children's books.
-
D.
Berlie Ray Dixon
Berlie Ray Dixon was the wife of American actor and director Ivan Dixon, known for her long marriage to him and her role in his personal life.
-
E.
Loren Long
Loren Long is an American children's book illustrator and author known for his richly detailed, nostalgic artwork in popular picture books and collaborations with prominent writers.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7e2416081908dfba48d7f7b4a84 |
completed | April 15, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9ddb46888190b1d2fe2992fc120b |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:59 a.m.