Triple

T6416197
Position Surface form Disambiguated ID Type / Status
Subject Payakumbuh E127834 entity
Predicate hasCulinarySpecialty P17589 FINISHED
Object gelamai
Gelamai is a traditional sweet delicacy from Payakumbuh, Indonesia, typically made from glutinous rice flour and palm sugar and known for its chewy, caramel-like texture.
E592427 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: gelamai | Statement: [Payakumbuh, hasCulinarySpecialty, gelamai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: gelamai
Context triple: [Payakumbuh, hasCulinarySpecialty, gelamai]
  • A. GEL
    GEL is the Georgian lari, the official currency used in the country of Georgia.
  • B. Gah
    Gah is a small village in present-day Pakistan best known as the birthplace of former Indian Prime Minister Manmohan Singh.
  • C. gon
    gon is the ISO 639-3 code for the Gondi language, a Dravidian language spoken by the Gond people in central India.
  • D. Gamilah
    Gamilah is one of the daughters of Malcolm X and Betty Shabazz, known for her connection to their civil rights legacy.
  • E. Gahal
    Gahal was a right-wing political alliance in Israel formed in the 1960s, primarily uniting the Herut movement with the Liberal Party and serving as a key predecessor to the Likud party.
  • 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: gelamai
Triple: [Payakumbuh, hasCulinarySpecialty, gelamai]
Generated description
Gelamai is a traditional sweet delicacy from Payakumbuh, Indonesia, typically made from glutinous rice flour and palm sugar and known for its chewy, caramel-like texture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: gelamai
Target entity description: Gelamai is a traditional sweet delicacy from Payakumbuh, Indonesia, typically made from glutinous rice flour and palm sugar and known for its chewy, caramel-like texture.
  • A. GEL
    GEL is the Georgian lari, the official currency used in the country of Georgia.
  • B. Gah
    Gah is a small village in present-day Pakistan best known as the birthplace of former Indian Prime Minister Manmohan Singh.
  • C. gon
    gon is the ISO 639-3 code for the Gondi language, a Dravidian language spoken by the Gond people in central India.
  • D. Gamilah
    Gamilah is one of the daughters of Malcolm X and Betty Shabazz, known for her connection to their civil rights legacy.
  • E. Gahal
    Gahal was a right-wing political alliance in Israel formed in the 1960s, primarily uniting the Herut movement with the Liberal Party and serving as a key predecessor to the Likud party.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c068e89c2c81909eeedc234e8ccde2 completed March 22, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640caaed881908ff9863b1b792ebc completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c641d6024c8190996aae40851a3b73 completed March 27, 2026, 8:37 a.m.
NED2 Entity disambiguation (via description) batch_69c6425e0a348190bc1eb90eb8c00597 completed March 27, 2026, 8:39 a.m.
Created at: March 22, 2026, 4:42 p.m.