Triple
T15392639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac Taylor |
E368085
|
entity |
| Predicate | colleague |
P398
|
FINISHED |
| Object | Sheldon Hawkes |
E353964
|
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: Sheldon Hawkes | Statement: [Mac Taylor, colleague, Sheldon Hawkes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheldon Hawkes Context triple: [Mac Taylor, colleague, Sheldon Hawkes]
-
A.
Sheldon Hawkes
chosen
Sheldon Hawkes is a brilliant former surgeon turned forensic pathologist and crime scene investigator on the television series CSI: NY.
-
B.
Sheldon Peck
Sheldon Peck was a 19th-century American folk artist and portrait painter known for his distinctive primitive style and abolitionist activities.
-
C.
Sheldon Fox
Sheldon Fox is an architect best known as one of the founding partners of the global architecture firm Kohn Pedersen Fox (KPF).
-
D.
Sheldon Lane
Sheldon Lane is an individual notable enough to be recognized as a prominent bearer of the surname Lane.
-
E.
Charles Leavitt
Charles Leavitt is an American screenwriter best known for writing the screenplay for the film "Blood Diamond."
- 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e7838b48190862b43c6c8620692 |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1350699c8190acf7830d88455851 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:19 a.m.