Triple
T16956727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas, Count of Perche |
E411324
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Count of Perche |
E899713
|
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 Perche | Statement: [Thomas, Count of Perche, title, Count of Perche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Count of Perche Context triple: [Thomas, Count of Perche, title, Count of Perche]
-
A.
Count of Perche
chosen
Count of Perche was a medieval French noble title associated with the Perche region, often held by members of the French royal and high aristocratic families.
-
B.
Count of Vaudémont
The Count of Vaudémont was a noble title held by a cadet branch of the House of Lorraine, associated with the lordship of Vaudémont in northeastern France.
-
C.
Count of Étampes
The Count of Étampes was a noble title in medieval France associated with the House of Évreux, linked to the lordship over the region of Étampes.
-
D.
Count of Auvergne
The Count of Auvergne was a medieval noble title associated with the rulers of the historic Auvergne region in central France.
-
E.
Surpierre
Surpierre is a small municipality in the canton of Fribourg in western Switzerland.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d01c7b408190b5a2b6c62b050b76 |
completed | April 18, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d4666f14819095fc3bcf5e459b61 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.