Triple
T23062670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nyad |
E574945
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Nyad |
—
|
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: Nyad | Statement: [Nyad, title, Nyad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nyad Context triple: [Nyad, title, Nyad]
-
A.
Nyad
chosen
Nyad is a biographical drama film depicting long-distance swimmer Diana Nyad's historic attempt to swim from Cuba to Florida at age 64.
-
B.
Dallas Seavey
Dallas Seavey is an American dog musher and multiple-time Iditarod Trail Sled Dog Race champion, known as one of the sport’s most successful competitors.
-
C.
Dressel
Dressel is the surname of American actress Trish Van Devere, known for her film and television work in the 1970s and 1980s.
-
D.
Ayana
Ayana is a short story by Stephen King, featured in his collection "Just After Sunset," that explores themes of miracles and mortality.
-
E.
Ederle
Ederle is the surname of Gertrude Ederle, the American competitive swimmer famed for being the first woman to swim across the English Channel.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a0c3c881909f137ad511c216ac |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.