Triple
T10996743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Gray |
E259891
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | John Shelby |
E262186
|
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: John Shelby | Statement: [Michael Gray, relative, John Shelby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Shelby Context triple: [Michael Gray, relative, John Shelby]
-
A.
John Shelby
chosen
John Shelby is a key member of the Shelby crime family in the British television series "Peaky Blinders," known for his fierce loyalty, volatility, and role in the gang's violent operations.
-
B.
Charles G. Smith
Charles G. Smith was an American engineer and businessman best known as a co-founder of the defense and aerospace company Raytheon.
-
C.
J. Dallas Dort
J. Dallas Dort was an American automobile pioneer and industrialist best known as the co-founder of the Durant-Dort Carriage Company, a key precursor to General Motors.
-
D.
Guy Wilkerson
Guy Wilkerson was an American character actor best known for his roles in Westerns and B-movies during the mid-20th century.
-
E.
John Cothran Jr.
John Cothran Jr. is an American character actor known for his supporting roles in film and television, including appearances in dramas and thrillers.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d795d6572c8190a47d68483863ad7a |
completed | April 9, 2026, 12:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4830a903481909eaf327457eabf2b |
completed | April 19, 2026, 7:23 a.m. |
Created at: April 8, 2026, 9:24 p.m.