Triple
T14066222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zelma Atwood |
E338478
|
entity |
| Predicate | hasLastName |
P18
|
FINISHED |
| Object | Atwood |
E436446
|
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: Atwood | Statement: [Zelma Atwood, hasLastName, Atwood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atwood Context triple: [Zelma Atwood, hasLastName, Atwood]
-
A.
Atwood
chosen
Atwood is a surname and place name most prominently associated with the acclaimed Canadian author Margaret Atwood.
-
B.
Vandermeer
Vandermeer is a surname of Dutch origin, commonly used as a variant spelling of "van der Meer."
-
C.
Applebaum
Applebaum is a Jewish-origin surname borne by various notable individuals in fields such as politics, academia, and the arts.
-
D.
Griffin Ondaatje
Griffin Ondaatje is a Canadian writer and filmmaker, known for his work in children's literature and documentaries and as the son of acclaimed author Michael Ondaatje.
-
E.
Dubrow
Dubrow is a surname most notably associated with American television personality and actress Heather Dubrow.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568b81f08190a571004261c0e8e4 |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb669111081909ccd167f41571a00 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.