Triple
T1657961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gertrude Ederle |
E35842
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Gertrude Caroline Ederle |
E35842
|
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: Gertrude Caroline Ederle | Statement: [Gertrude Ederle, fullName, Gertrude Caroline Ederle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gertrude Caroline Ederle Context triple: [Gertrude Ederle, fullName, Gertrude Caroline Ederle]
-
A.
Gertrude Ederle
chosen
Gertrude Ederle was an American competitive swimmer who became the first woman to swim across the English Channel, breaking the existing men's record in 1926.
-
B.
Louise Arner Boyd
Louise Arner Boyd was an American explorer and photographer renowned for her pioneering Arctic expeditions in the early 20th century.
-
C.
Mildred Watkins
Mildred Watkins was the wife of American politician and baseball commissioner Happy Chandler.
-
D.
Eileen Soper
Eileen Soper was a British illustrator and etcher best known for her lively illustrations in Enid Blyton’s children’s books.
-
E.
Esther Williams
Esther Williams was an American competitive swimmer-turned-Hollywood star best known for her aquatic-themed musical films in the 1940s and 1950s.
- 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90aafe5e881908158fab83998fd07 |
completed | March 5, 2026, 4:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad68254a6081909c2222fd77dff648 |
completed | March 8, 2026, 12:14 p.m. |
Created at: March 4, 2026, 7:29 p.m.