Triple

T11494550
Position Surface form Disambiguated ID Type / Status
Subject East New Britain Province E272500 entity
Predicate hasMajorTown P316 FINISHED
Object Kerevat
Kerevat is a significant inland town in East New Britain Province of Papua New Guinea, known for its agricultural research station and surrounding cocoa and coconut plantations.
E929076 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: Kerevat | Statement: [East New Britain Province, hasMajorTown, Kerevat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kerevat
Context triple: [East New Britain Province, hasMajorTown, Kerevat]
  • A. Larevat
    Larevat is an Oceanic language spoken in Vanuatu, closely related to and geographically near the Uripiv-Wala-Rano-Atchin language cluster.
  • B. Kezlev
    Kezlev is the historical Crimean Tatar name for the city now known as Eupatoria, a coastal town on the western shore of Crimea.
  • C. Keratea
    Keratea is a town in eastern Attica, Greece, known for its historical significance and proximity to the Athens metropolitan area.
  • D. Kehre
    Kehre is a key concept in Martin Heidegger’s philosophy denoting a decisive “turn” or shift in his thinking about Being and the history of Western metaphysics.
  • E. Kove
    Kove is an Austronesian language spoken in coastal communities of New Britain in Papua New Guinea.
  • 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: Kerevat
Triple: [East New Britain Province, hasMajorTown, Kerevat]
Generated description
Kerevat is a significant inland town in East New Britain Province of Papua New Guinea, known for its agricultural research station and surrounding cocoa and coconut plantations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kerevat
Target entity description: Kerevat is a significant inland town in East New Britain Province of Papua New Guinea, known for its agricultural research station and surrounding cocoa and coconut plantations.
  • A. Larevat
    Larevat is an Oceanic language spoken in Vanuatu, closely related to and geographically near the Uripiv-Wala-Rano-Atchin language cluster.
  • B. Kezlev
    Kezlev is the historical Crimean Tatar name for the city now known as Eupatoria, a coastal town on the western shore of Crimea.
  • C. Keratea
    Keratea is a town in eastern Attica, Greece, known for its historical significance and proximity to the Athens metropolitan area.
  • D. Kehre
    Kehre is a key concept in Martin Heidegger’s philosophy denoting a decisive “turn” or shift in his thinking about Being and the history of Western metaphysics.
  • E. Kove
    Kove is an Austronesian language spoken in coastal communities of New Britain in Papua New Guinea.
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85ddffdf88190a00e94ad5b8b91a5 completed April 10, 2026, 2:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6048a05c88190968f7827c5dd5342 completed April 20, 2026, 10:48 a.m.
NEDg Description generation batch_69e610a6de0c8190aabda7ef7b7063a6 completed April 20, 2026, 11:40 a.m.
NED2 Entity disambiguation (via description) batch_69e61842b8848190b454cee480c69f7a completed April 20, 2026, 12:12 p.m.
Created at: April 8, 2026, 9:36 p.m.