Triple
T21811166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Travers |
E538474
|
entity |
| Predicate | relativeOf |
P367
|
FINISHED |
| Object | Tom Travers |
—
|
NE NERFINISHED |
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: Tom Travers | Statement: [Mrs. Travers, relativeOf, Tom Travers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Travers Context triple: [Mrs. Travers, relativeOf, Tom Travers]
-
A.
Tom Travers
chosen
Tom Travers is a fictional character in P. G. Wodehouse’s Jeeves and Wooster stories, known as the genial, somewhat henpecked country squire married to the formidable Aunt Dahlia.
-
B.
John Powers
John Powers is a relatively common personal name shared by multiple individuals across fields such as politics, sports, and the arts, rather than referring to a single widely recognized figure.
-
C.
Calvin Tomkins
Calvin Tomkins is an American art critic and author best known for his long-running profiles of contemporary artists in The New Yorker.
-
D.
David Goodis
David Goodis was an American noir and hardboiled crime novelist known for his bleak, psychologically driven stories of down-and-out characters.
-
E.
Kevin Crowe
Kevin Crowe is a songwriter best known for co-writing the hit track "Young, Wild & Free."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc6cdf88190a31129acdc3bcec8 |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:53 p.m.