Triple
T2738002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katharine Towne |
E60675
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Monk |
E70296
|
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: Monk | Statement: [Katharine Towne, notableWork, Monk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Monk Context triple: [Katharine Towne, notableWork, Monk]
-
A.
Monk
chosen
Monk is an American comedy-drama detective television series centered on the brilliant but obsessive-compulsive private investigator Adrian Monk.
-
B.
Monk
Monk is a surname most prominently associated with Art Monk, the Hall of Fame former NFL wide receiver for the Washington Redskins.
-
C.
Uncle Monk
Uncle Monk is an acoustic bluegrass and old-time music duo co-founded by former Ramones drummer Tommy Ramone.
-
D.
Mr. Teabag
Mr. Teabag is a comically absurd civil servant portrayed by John Cleese in Monty Python’s “Ministry of Silly Walks” sketch, known for his exaggerated, nonsensical way of walking.
-
E.
Monk Lewis
Monk Lewis was the pseudonym of Matthew Gregory Lewis, an English Gothic novelist and dramatist best known for his sensational 1796 novel "The Monk."
- 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_69ab4b77febc819095603eb012cd141b |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb147a588190829b74fe05b3a114 |
completed | March 7, 2026, 8 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afb6a5dda0819092508b9e10030d09 |
completed | March 10, 2026, 6:13 a.m. |
Created at: March 6, 2026, 9:56 p.m.