Triple
T18263998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alma Wheatley |
E437434
|
entity |
| Predicate | hasSurname |
P18
|
FINISHED |
| Object | Wheatley |
—
|
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: Wheatley | Statement: [Alma Wheatley, hasSurname, Wheatley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wheatley Context triple: [Alma Wheatley, hasSurname, Wheatley]
-
A.
Wheatley
Wheatley is a small community in southwestern Ontario, Canada, known for its proximity to Lake Erie and Wheatley Provincial Park.
-
B.
Wheatley
Wheatley is a large village and civil parish in South Oxfordshire, England, known for its historic center and proximity to Oxford.
-
C.
Wheatley
chosen
Wheatley is the surname given to Phillis Wheatley, the first published African American female poet and an important figure in early American literature.
-
D.
Wheatley (Portal 2)
Wheatley (Portal 2) is a comically inept yet pivotal personality core from the video game Portal 2, known for his humorous dialogue and central role in the game's story.
-
E.
GLaDOS
GLaDOS is the sinister, sarcastic artificial intelligence antagonist from Valve’s Portal video game series.
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ff78b188819081da8e1d389c6c79 |
completed | April 19, 2026, 4:14 p.m. |
Created at: April 10, 2026, 10:34 a.m.