Triple
T11884192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franklin |
E282733
|
entity |
| Predicate | taleGenre |
P11858
|
FINISHED |
| Object | Breton lai |
E951580
|
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: Breton lai | Statement: [Franklin, taleGenre, Breton lai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Breton lai Context triple: [Franklin, taleGenre, Breton lai]
-
A.
Breton lai
chosen
A Breton lai is a short medieval narrative poem, often involving romance, chivalry, and the supernatural, traditionally associated with Brittany and written in verse.
-
B.
Le Breton
Le Breton is a French surname borne by various notable figures, including publishers, politicians, and artists.
-
C.
Lebreton
Lebreton is a French surname, often a variant of "Le Breton," historically denoting someone from Brittany (Bretagne) in France.
-
D.
Brionnais
Brionnais is a historic rural region in eastern France known for its Romanesque churches, traditional stone villages, and Charolais cattle farming.
-
E.
Mor Breizh
Mor Breizh is the Breton name for the English Channel, the arm of the Atlantic Ocean that separates southern England from northern France.
- 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_69d6ab2a90b08190a4e818821cc93e6d |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903024afc8190a97aa3263dc7d017 |
completed | April 10, 2026, 2:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f417da310c8190aa04df2a316a5dd0 |
completed | May 1, 2026, 3:02 a.m. |
Created at: April 8, 2026, 9:44 p.m.