Triple

T12792229
Position Surface form Disambiguated ID Type / Status
Subject canton of Romans-sur-Isère E305795 entity
Predicate contains P35 FINISHED
Object Hostun
Hostun is a small commune in southeastern France’s Drôme department, known for its rural setting at the foot of the Vercors massif.
E1003105 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: Hostun | Statement: [canton of Romans-sur-Isère, contains, Hostun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hostun
Context triple: [canton of Romans-sur-Isère, contains, Hostun]
  • A. Hoste
    Hoste is a mathematician known for his contributions to knot theory, including work related to the HOMFLY-PT polynomial.
  • B. Hostomel
    Hostomel is a town near Kyiv in northern Ukraine, known for its strategic airport and its role in the early stages of the 2022 Russian invasion.
  • C. Hostouň
    Hostouň is a small town and municipality in the Plzeň Region of the Czech Republic, known for its rural character and historical setting near the German border.
  • D. Unhos
    Unhos is a civil parish in the municipality of Loures, within the Lisbon District of Portugal.
  • E. d’Hostun
    d’Hostun is a French noble family name historically associated with military leaders such as Marshal Tallard.
  • 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: Hostun
Triple: [canton of Romans-sur-Isère, contains, Hostun]
Generated description
Hostun is a small commune in southeastern France’s Drôme department, known for its rural setting at the foot of the Vercors massif.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hostun
Target entity description: Hostun is a small commune in southeastern France’s Drôme department, known for its rural setting at the foot of the Vercors massif.
  • A. Hoste
    Hoste is a mathematician known for his contributions to knot theory, including work related to the HOMFLY-PT polynomial.
  • B. Hostomel
    Hostomel is a town near Kyiv in northern Ukraine, known for its strategic airport and its role in the early stages of the 2022 Russian invasion.
  • C. Hostouň
    Hostouň is a small town and municipality in the Plzeň Region of the Czech Republic, known for its rural character and historical setting near the German border.
  • D. Unhos
    Unhos is a civil parish in the municipality of Loures, within the Lisbon District of Portugal.
  • E. d’Hostun
    d’Hostun is a French noble family name historically associated with military leaders such as Marshal Tallard.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e6b55248190ab938e69eb263612 completed April 10, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6850ac1808190a9b547d934252d10 completed May 2, 2026, 11:13 p.m.
NEDg Description generation batch_69f689733f748190bca592ab30b4437c completed May 2, 2026, 11:32 p.m.
NED2 Entity disambiguation (via description) batch_69f68a4cb2c4819083def0a43452470f completed May 2, 2026, 11:35 p.m.
Created at: April 9, 2026, 5:30 p.m.