Triple

T5130043
Position Surface form Disambiguated ID Type / Status
Subject Zangezur Mountains E115673 entity
Predicate nearbyCity P350 FINISHED
Object Kapan
Kapan is a town in southern Armenia that serves as an important regional center nestled in the Zangezur mountain range.
 E496099 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: Kapan | Statement: [Zangezur Mountains, nearbyCity, Kapan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kapan
Context triple: [Zangezur Mountains, nearbyCity, Kapan]
  • A. Nzaman
    Nzaman is a dialect of the Fang language spoken by Fang communities in Central Africa.
  • B. Kini
    Kini is a small coastal village and popular beach resort on the Greek island of Syros in the Cyclades.
  • C. Kapit
    Kapit is a remote riverside town and administrative center in Sarawak, Malaysia, known historically as a trading post accessible mainly by boat along the Rajang River.
  • D. Dimasa
    Dimasa is a Tibeto-Burman language spoken primarily by the Dimasa people in parts of Northeast India, including the Barak Valley region.
  • E. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of 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: Kapan
Triple: [Zangezur Mountains, nearbyCity, Kapan]
Generated description
Kapan is a town in southern Armenia that serves as an important regional center nestled in the Zangezur mountain range.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kapan
Target entity description: Kapan is a town in southern Armenia that serves as an important regional center nestled in the Zangezur mountain range.
  • A. Nzaman
    Nzaman is a dialect of the Fang language spoken by Fang communities in Central Africa.
  • B. Kini
    Kini is a small coastal village and popular beach resort on the Greek island of Syros in the Cyclades.
  • C. Kapit
    Kapit is a remote riverside town and administrative center in Sarawak, Malaysia, known historically as a trading post accessible mainly by boat along the Rajang River.
  • D. Dimasa
    Dimasa is a Tibeto-Burman language spoken primarily by the Dimasa people in parts of Northeast India, including the Barak Valley region.
  • E. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7827c764819086da3b79f2020224 completed March 20, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4c23d5c8190883a297254d9c80d completed March 21, 2026, 4:18 p.m.
NEDg Description generation batch_69bec6620aac8190a820190e7facd70a completed March 21, 2026, 4:25 p.m.
NED2 Entity disambiguation (via description) batch_69bec70062f48190baae277e6f8c5c4e completed March 21, 2026, 4:27 p.m.
Created at: March 20, 2026, 1:42 p.m.