Triple
T21126812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Welsh |
E520578
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object |
Old Breton
Old Breton is an extinct Brythonic Celtic language once spoken in Brittany, closely related to Old Welsh and ancestral to modern Breton.
|
E1467691
|
NE FINISHED |
How this triple was built (4 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: Old Breton | Statement: [Old Welsh, closelyRelatedTo, Old Breton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Old Breton Context triple: [Old Welsh, closelyRelatedTo, Old Breton]
-
A.
Olden
Olden is a surname most notably associated with Charles Smith Olden, a 19th-century American politician who served as Governor of New Jersey.
-
B.
Olden
Olden is a small village in Stryn Municipality in Vestland county, Norway, known as a gateway to the Nordfjord region and nearby glaciers.
-
C.
Old French sire
Old French "sire" is a historical term of respect and address that evolved into the English honorific "sir."
-
D.
Old Norman
Old Norman is a medieval Romance language that developed in Normandy from Latin and significantly influenced the vocabulary of English and other regional languages.
-
E.
Breton lai
A Breton lai is a short medieval narrative poem, often involving romance, chivalry, and the supernatural, traditionally associated with Brittany and written in verse.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Old Breton Triple: [Old Welsh, closelyRelatedTo, Old Breton]
Generated description
Old Breton is an extinct Brythonic Celtic language once spoken in Brittany, closely related to Old Welsh and ancestral to modern Breton.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Old Breton Target entity description: Old Breton is an extinct Brythonic Celtic language once spoken in Brittany, closely related to Old Welsh and ancestral to modern Breton.
-
A.
Olden
Olden is a surname most notably associated with Charles Smith Olden, a 19th-century American politician who served as Governor of New Jersey.
-
B.
Olden
Olden is a small village in Stryn Municipality in Vestland county, Norway, known as a gateway to the Nordfjord region and nearby glaciers.
-
C.
Old French sire
Old French "sire" is a historical term of respect and address that evolved into the English honorific "sir."
-
D.
Old Norman
Old Norman is a medieval Romance language that developed in Normandy from Latin and significantly influenced the vocabulary of English and other regional languages.
-
E.
Breton lai
A Breton lai is a short medieval narrative poem, often involving romance, chivalry, and the supernatural, traditionally associated with Brittany and written in verse.
- F. None of above. chosen
Provenance (5 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_69e0b50a623881909c0bbaf4f2c055e7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72239965c819081b4077b914d0a98 |
completed | April 21, 2026, 7:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0965ee05c0819084273a47c09d7d2f |
completed | May 17, 2026, 6:53 a.m. |
| NEDg | Description generation | batch_6a09669ac9988190ba5ec8bcf8dc7eb4 |
completed | May 17, 2026, 6:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0967821ce08190a23d22439c343f49 |
completed | May 17, 2026, 7 a.m. |
Created at: April 16, 2026, 2:56 p.m.