Triple

T22405721
Position Surface form Disambiguated ID Type / Status
Subject canton of Apt E553875 entity
Predicate contains P35 FINISHED
Object Mane
Mane is a small commune in southeastern France known for its historic Provençal architecture and picturesque setting in the Alpes-de-Haute-Provence department.
 E1533674 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: Mane | Statement: [canton of Apt, contains, Mane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mane
Context triple: [canton of Apt, contains, Mane]
  • A. Manes
    Manes are the benevolent ancestral spirits of the dead in ancient Roman religion, venerated as protectors of the family and household.
  • B. Roan
    Roan is a masculine given name of English origin, often associated with a reddish-brown color or a type of horse coat pattern.
  • C. Roan
    Roan is a coastal municipality in Trøndelag county, Norway, known for its rugged shoreline, fishing traditions, and wind power resources.
  • D. Roan
    Roan is a prominent character from the television series "The 100," known as the stoic and formidable King of the Ice Nation.
  • E. Mander
    The Mander is the longest and most significant river in the Reach, a fertile region of Westeros in George R. R. Martin’s A Song of Ice and Fire series.
  • 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: Mane
Triple: [canton of Apt, contains, Mane]
Generated description
Mane is a small commune in southeastern France known for its historic Provençal architecture and picturesque setting in the Alpes-de-Haute-Provence department.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mane
Target entity description: Mane is a small commune in southeastern France known for its historic Provençal architecture and picturesque setting in the Alpes-de-Haute-Provence department.
  • A. Manes
    Manes are the benevolent ancestral spirits of the dead in ancient Roman religion, venerated as protectors of the family and household.
  • B. Roan
    Roan is a coastal municipality in Trøndelag county, Norway, known for its rugged shoreline, fishing traditions, and wind power resources.
  • C. Roan
    Roan is a masculine given name of English origin, often associated with a reddish-brown color or a type of horse coat pattern.
  • D. Roan
    Roan is a prominent character from the television series "The 100," known as the stoic and formidable King of the Ice Nation.
  • E. Mander
    The Mander is the longest and most significant river in the Reach, a fertile region of Westeros in George R. R. Martin’s A Song of Ice and Fire series.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b739b88190a7f1f20fd1e9b188 completed April 29, 2026, 1:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae9cfabe081908d6a001bcfe5372c completed May 18, 2026, 10:28 a.m.
NEDg Description generation batch_6a0aea5eef848190893c8b7f6066092d completed May 18, 2026, 10:30 a.m.
NED2 Entity disambiguation (via description) batch_6a0aeaf55efc81909438a39cbfd5e723 completed May 18, 2026, 10:33 a.m.
Created at: April 16, 2026, 8:46 p.m.