Triple
T4495447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isaac Shelby |
E100683
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Shelby |
E349953
|
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: Shelby | Statement: [Isaac Shelby, familyName, Shelby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shelby Context triple: [Isaac Shelby, familyName, Shelby]
-
A.
Shelby
chosen
Shelby is a fictional character known for serving as a coach, typically portrayed as a mentor and leader within a sports or team setting.
-
B.
Aiken
Aiken is a variant spelling of the surname Aitken, which is of Scottish origin.
-
C.
Elmore
Elmore is the birth name of American actor Rip Torn, a prolific character performer known for his intense screen presence and roles in projects like "The Larry Sanders Show" and "Men in Black."
-
D.
Winfield
Winfield is a masculine given name most notably borne by 19th-century American military leader Winfield Scott.
-
E.
Pelham
Pelham is the first name of P. G. Wodehouse, the celebrated English humorist and author known for his Jeeves and Wooster stories.
- 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_69bd43cdf15081909a4fa2585ff63b3e |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd56bde14c819091d42839a46291d0 |
completed | March 20, 2026, 2:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bd67bfb4788190b64975b1999a8d1e |
completed | March 20, 2026, 3:29 p.m. |
Created at: March 20, 2026, 1 p.m.