Triple

T5906940
Position Surface form Disambiguated ID Type / Status
Subject Grande Terre E131362 entity
Predicate hasMajorCity P316 FINISHED
Object Koné
Koné is a principal town and administrative center on New Caledonia’s main island, Grande Terre.
 E553227 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: Koné | Statement: [Grande Terre, hasMajorCity, Koné]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koné
Context triple: [Grande Terre, hasMajorCity, Koné]
  • A. Duékoué
    Duékoué is a town in western Côte d'Ivoire that became notorious as a major site of violence and massacres during the country's civil conflicts.
  • B. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • C. Langoué Baï
    Langoué Baï is a renowned forest clearing in Gabon celebrated for its rich biodiversity and frequent gatherings of forest elephants and other wildlife.
  • D. Ndesandjo
    Ndesandjo is the surname of Mark Obama Ndesandjo, an American businessman, musician, and author who is the half-brother of former U.S. President Barack Obama.
  • E. Khondji
    Khondji is the surname of Darius Khondji, a renowned cinematographer known for his visually distinctive work on international films.
  • 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: Koné
Triple: [Grande Terre, hasMajorCity, Koné]
Generated description
Koné is a principal town and administrative center on New Caledonia’s main island, Grande Terre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koné
Target entity description: Koné is a principal town and administrative center on New Caledonia’s main island, Grande Terre.
  • A. Duékoué
    Duékoué is a town in western Côte d'Ivoire that became notorious as a major site of violence and massacres during the country's civil conflicts.
  • B. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • C. Langoué Baï
    Langoué Baï is a renowned forest clearing in Gabon celebrated for its rich biodiversity and frequent gatherings of forest elephants and other wildlife.
  • D. Ndesandjo
    Ndesandjo is the surname of Mark Obama Ndesandjo, an American businessman, musician, and author who is the half-brother of former U.S. President Barack Obama.
  • E. Khondji
    Khondji is the surname of Darius Khondji, a renowned cinematographer known for his visually distinctive work on international films.
  • 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_69c0085864a88190a569c05ff7d65f29 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03772d9dc8190899fe49ef887e685 completed March 22, 2026, 6:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b16ba6c881908e9a909bf86ea92d completed March 23, 2026, 3:20 a.m.
NEDg Description generation batch_69c0b2751c2081908c8d47c9c0c26e84 completed March 23, 2026, 3:24 a.m.
NED2 Entity disambiguation (via description) batch_69c0b2d6d5688190936858046377d192 completed March 23, 2026, 3:26 a.m.
Created at: March 22, 2026, 3:59 p.m.