Triple

T12478182
Position Surface form Disambiguated ID Type / Status
Subject Region I E298230 entity
Predicate hasCity P316 FINISHED
Object Candon
Candon is a component city in the province of Ilocos Sur in the Philippines, known for its tobacco industry and the famed "Candon Dwarf" mangoes.
E984118 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: Candon | Statement: [Region I, hasCity, Candon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Candon
Context triple: [Region I, hasCity, Candon]
  • A. Itogon
    Itogon is a mountainous municipality in Benguet province in the Philippines, known for its mining industry and scenic river valleys.
  • B. Menlale
    Menlale is an alternative name for Mount Foraker, a prominent peak in the Alaska Range and one of the highest mountains in North America.
  • C. Surigaonon
    Surigaonon is a Visayan language spoken primarily in the Caraga region of northeastern Mindanao in the Philippines.
  • D. Tinogasta
    Tinogasta is a town in northwestern Argentina known for its wine production, hot springs, and location along the Andean mountain routes in Catamarca Province.
  • E. Hinatuan
    Hinatuan is a coastal municipality in the province of Surigao del Sur in the Philippines, best known for its clear blue Hinatuan Enchanted River.
  • 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: Candon
Triple: [Region I, hasCity, Candon]
Generated description
Candon is a component city in the province of Ilocos Sur in the Philippines, known for its tobacco industry and the famed "Candon Dwarf" mangoes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Candon
Target entity description: Candon is a component city in the province of Ilocos Sur in the Philippines, known for its tobacco industry and the famed "Candon Dwarf" mangoes.
  • A. Itogon
    Itogon is a mountainous municipality in Benguet province in the Philippines, known for its mining industry and scenic river valleys.
  • B. Menlale
    Menlale is an alternative name for Mount Foraker, a prominent peak in the Alaska Range and one of the highest mountains in North America.
  • C. Surigaonon
    Surigaonon is a Visayan language spoken primarily in the Caraga region of northeastern Mindanao in the Philippines.
  • D. Tinogasta
    Tinogasta is a town in northwestern Argentina known for its wine production, hot springs, and location along the Andean mountain routes in Catamarca Province.
  • E. Hinatuan
    Hinatuan is a coastal municipality in the province of Surigao del Sur in the Philippines, best known for its clear blue Hinatuan Enchanted River.
  • 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_69d6ada377208190a36011199a4d8558 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94dcc24e48190ae9c367a03f659f4 completed April 10, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f2732a08190890493925e41a6e1 completed May 2, 2026, 6:15 p.m.
NEDg Description generation batch_69f640b513488190893359e9964dbe98 completed May 2, 2026, 6:21 p.m.
NED2 Entity disambiguation (via description) batch_69f641abe114819093d99a327f2220c2 completed May 2, 2026, 6:25 p.m.
Created at: April 8, 2026, 9:56 p.m.