Triple
T9245875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philip the Good |
E222192
|
entity |
| Predicate | positionHeld |
P8
|
FINISHED |
| Object | Count of Charolais |
E747708
|
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: Count of Charolais | Statement: [Philip the Good, positionHeld, Count of Charolais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Count of Charolais Context triple: [Philip the Good, positionHeld, Count of Charolais]
-
A.
Count of Charolais
chosen
The Count of Charolais was a noble title in the Burgundian Netherlands, notably held by Charles the Rash before he became Duke of Burgundy.
-
B.
Charolais
Charolais is a historic rural region in eastern France renowned for its high-quality beef cattle and rich agricultural traditions.
-
C.
Nivernais cattle
Nivernais cattle are a traditional French draught and beef cattle breed originating from the Nivernais region, known for their strength and distinctive dark coat.
-
D.
Hereford cattle
Hereford cattle are a widely recognized British beef breed known for their distinctive red bodies with white faces, hardiness, and efficient meat production.
-
E.
Limousin
Limousin is a former administrative region in central France known for its rural landscapes, cattle breeding, and historic towns such as Limoges and Tulle.
- 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_69ca841d2b18819089f9faf5b2c2aec0 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd03f181e081908d9ff7dc6f86420e |
completed | April 1, 2026, 11:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d077f14804819098f443a2517ad461 |
completed | April 4, 2026, 2:31 a.m. |
Created at: March 30, 2026, 7:30 p.m.