Triple
T15311962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mud |
E366058
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | David Wingo |
E385697
|
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: David Wingo | Statement: [Mud, musicBy, David Wingo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Wingo Context triple: [Mud, musicBy, David Wingo]
-
A.
David Wingo
chosen
David Wingo is an American film and television composer known for his atmospheric, character-driven scores for independent dramas and series such as "Take Shelter," "Mud," and HBO's "Barry."
-
B.
Richard Wingo
Richard Wingo is an American R&B singer best known as a member of the vocal group Jagged Edge.
-
C.
Tom Wingo
Tom Wingo is the troubled Southern football coach and teacher who confronts his painful family history while helping his sister’s psychiatrist uncover the roots of her trauma in *The Prince of Tides*.
-
D.
George Wing
George Wing is an American screenwriter best known for writing the romantic comedy film "50 First Dates."
-
E.
Sam Wright
Sam Wright is an individual known primarily as a relative of George Wright.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd2d5a88190aead748920f93d47 |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff133d171c8190918c9624bcdb7451 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:16 a.m.