Triple
T22542984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fannie N. Smith |
E557342
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Fannie |
—
|
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: Fannie | Statement: [Fannie N. Smith, givenName, Fannie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fannie Context triple: [Fannie N. Smith, givenName, Fannie]
-
A.
Fannie
chosen
Fannie is a feminine given name, often used in English-speaking countries and historically associated with figures such as the American cookbook author Fannie Farmer.
-
B.
Ettie
Ettie is the official chicken-inspired mascot created for the 2019 FIFA Women’s World Cup in France.
-
C.
Nell Van Dort
Nell Van Dort is a character in Tim Burton's animated film "Corpse Bride," depicted as the socially ambitious and somewhat overbearing mother of Victor Van Dort.
-
D.
Doris
Doris is the given name of Doris Buffett, an American philanthropist and sister of investor Warren Buffett, known for her charitable work and focus on direct, person-to-person giving.
-
E.
Doris
Doris is the central character of the work "Blonde Roots," around whom the story’s events and themes revolve.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f330a40819098df6a9b0f27635e |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.