Triple
T22026712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evelyn Nesbit |
E543984
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Nesbit |
—
|
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: Nesbit | Statement: [Evelyn Nesbit, familyName, Nesbit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nesbit Context triple: [Evelyn Nesbit, familyName, Nesbit]
-
A.
Nesbit
chosen
Nesbit is an English surname most famously associated with E. Nesbit, the pioneering author of classic children's literature such as "The Railway Children."
-
B.
Beatrice Bentley
Beatrice Bentley was an actress known for her role in the early Technicolor silent film "The Toll of the Sea."
-
C.
Maesa Pullman
Maesa Pullman is an American singer-songwriter and musician, known for her indie-folk work and as the daughter of actor Bill Pullman.
-
D.
Hazel Wood
Hazel Wood is a country park area near Corby in Northamptonshire, England, known for its woodland walks and local wildlife.
-
E.
Alice de Hales
Alice de Hales was an English noblewoman of the early 14th century, best known as the wife of Thomas of Brotherton, 1st Earl of Norfolk and son of King Edward I.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ccc2ec8190a94d69530d00c06c |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:24 p.m.