Triple
T20043871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Geyser |
E497500
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Mary Geyser |
—
|
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: Mary Geyser | Statement: [Mary Geyser, hasName, Mary Geyser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Geyser Context triple: [Mary Geyser, hasName, Mary Geyser]
-
A.
Mary Geyser
chosen
Mary Geyser is the central fictional protagonist of the historical novel "The Blue and the Gray," which explores personal and social struggles during the American Civil War.
-
B.
Gail Jensen
Gail Jensen was an American actress and the second wife of actor David Carradine.
-
C.
Barbara Kean
Barbara Kean is a character in the Batman universe, often depicted as James Gordon’s wife and the mother of Batgirl, with varying portrayals across comics, films, and television adaptations.
-
D.
Annmarie Fulton
Annmarie Fulton is an actress best known for her role in the film "Sweet Sixteen."
-
E.
Diana Munson
Diana Munson is the widow of New York Yankees catcher and captain Thurman Munson, known for preserving his legacy and remaining active in charitable and commemorative events related to his life and career.
- 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_69da627278c88190babe4297a9df1236 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e662ed59bc8190a9ff25493e500ebb |
completed | April 20, 2026, 5:31 p.m. |
Created at: April 11, 2026, 3:37 p.m.