Triple
T13353825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Tallard |
E318135
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | d’Hostun |
E316253
|
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: d’Hostun | Statement: [Duke of Tallard, familyName, d’Hostun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: d’Hostun Context triple: [Duke of Tallard, familyName, d’Hostun]
-
A.
d’Hostun
chosen
d’Hostun is a French noble family name historically associated with military leaders such as Marshal Tallard.
-
B.
Heustreu
Heustreu is a small municipality in the Rhön-Grabfeld district of northern Bavaria, Germany, known for its rural character and location near the Rhön Mountains.
-
C.
Longuyon
Longuyon is a commune in northeastern France’s Meurthe-et-Moselle department, near the borders with Belgium and Luxembourg, known for its strategic location and historical military presence.
-
D.
Régiolis
Régiolis is a family of modern, modular multiple-unit regional trains built by Alstom for France’s TER networks, designed for improved comfort, efficiency, and accessibility.
-
E.
Audinghen
Audinghen is a small coastal commune in northern France known for its proximity to the scenic Cap Gris-Nez headland on the English Channel.
- 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8d520881908aa23c7102b72b72 |
completed | April 11, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f49e5548190b14d09daea628e6b |
completed | May 3, 2026, 10:11 a.m. |
Created at: April 9, 2026, 9:32 p.m.