Triple

T21809343
Position Surface form Disambiguated ID Type / Status
Subject arrondissement of Riom E538429 entity
Predicate contains P35 FINISHED
Object Randan
Randan is a commune in central France’s Puy-de-Dôme department, known for its historic Château de Randan estate and surrounding parklands.
 E1502827 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: Randan | Statement: [arrondissement of Riom, contains, Randan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Randan
Context triple: [arrondissement of Riom, contains, Randan]
  • A. Rander
    Rander is a historic suburb of Surat in the Indian state of Gujarat, known for its old trading community and cultural heritage.
  • B. Ranon
    Ranon is a small village located on Ambrym Island in the archipelago nation of Vanuatu in the South Pacific.
  • C. Ranjen
    Ranjen is a lower-ranking Bajoran religious title within the faith’s clerical hierarchy in the Star Trek universe.
  • D. Rande
    Rande is a masculine given name most notably borne by American businessman and former model Rande Gerber.
  • E. Raybūn
    Raybūn is an ancient settlement site in the Hadramawt region of Yemen, known from archaeological remains associated with the Hadramite civilization.
  • 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: Randan
Triple: [arrondissement of Riom, contains, Randan]
Generated description
Randan is a commune in central France’s Puy-de-Dôme department, known for its historic Château de Randan estate and surrounding parklands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Randan
Target entity description: Randan is a commune in central France’s Puy-de-Dôme department, known for its historic Château de Randan estate and surrounding parklands.
  • A. Rander
    Rander is a historic suburb of Surat in the Indian state of Gujarat, known for its old trading community and cultural heritage.
  • B. Ranon
    Ranon is a small village located on Ambrym Island in the archipelago nation of Vanuatu in the South Pacific.
  • C. Ranjen
    Ranjen is a lower-ranking Bajoran religious title within the faith’s clerical hierarchy in the Star Trek universe.
  • D. Rande
    Rande is a masculine given name most notably borne by American businessman and former model Rande Gerber.
  • E. Raybūn
    Raybūn is an ancient settlement site in the Hadramawt region of Yemen, known from archaeological remains associated with the Hadramite civilization.
  • 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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07cc4809c8190853e2777a1f573d4 completed April 28, 2026, 9:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e88cf888190b185e72216cdf44f completed May 17, 2026, 10:17 p.m.
NEDg Description generation batch_6a0a3f31d4788190a5b7d3678c2dd432 completed May 17, 2026, 10:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0a402328f88190aedece0522614d71 completed May 17, 2026, 10:24 p.m.
Created at: April 16, 2026, 6:53 p.m.