Triple
T9924440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gertrude Ederle |
E187884
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Ederle |
E187884
|
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: Ederle | Statement: [Gertrude Ederle, familyName, Ederle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ederle Context triple: [Gertrude Ederle, familyName, Ederle]
-
A.
Ederle
chosen
Ederle is the surname of Gertrude Ederle, the American competitive swimmer famed for being the first woman to swim across the English Channel.
-
B.
Casermo Ederle
Caserma Ederle is a major U.S. Army installation in Vicenza, Italy, serving as a key hub for American military operations and support in Europe and Africa.
-
C.
Nauta
Nauta is a small river port town in Peru’s Loreto region, serving as a key gateway for tourism and access to the Pacaya-Samiria National Reserve in the Amazon rainforest.
-
D.
Jolanda
Jolanda is a feminine given name, commonly considered a variant of Yolanda, used in various European countries.
-
E.
Cariane
Cariane was a French public transport operator that managed bus and coach services before being succeeded by Keolis.
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb598651081908286763ff56ba57c |
completed | April 2, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20e143660819097a9fa96365bc25a |
completed | April 5, 2026, 7:24 a.m. |
Created at: March 30, 2026, 8:43 p.m.