Triple

T23483890
Position Surface form Disambiguated ID Type / Status
Subject ASEAN Trade in Goods Agreement E570477 entity
Predicate shortName P43 FINISHED
Object ATIGA
ATIGA is a key ASEAN agreement that aims to liberalize and facilitate trade in goods among member states by reducing tariffs and harmonizing trade rules.
 E1587478 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: ATIGA | Statement: [ASEAN Trade in Goods Agreement, shortName, ATIGA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ATIGA
Context triple: [ASEAN Trade in Goods Agreement, shortName, ATIGA]
  • A. ATIA
    ATIA is the commonly used acronym for Canada’s federal Access to Information Act, which grants the public a legal right to access government records.
  • B. Atiim
    Atiim is the given first name of former NFL running back and sports media personality Tiki Barber.
  • C. Atadage
    Atadage is an ancient stone temple in the medieval Sri Lankan city of Polonnaruwa, believed to have housed the Sacred Tooth Relic of the Buddha.
  • D. AITI
    AITI is an organization known for sponsoring and supporting initiatives related to the Bengali-language internet domain .bn.
  • E. AITI
    AITI is the national regulatory authority overseeing Brunei Darussalam’s information and communications technology (ICT) and telecommunications sectors.
  • 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: ATIGA
Triple: [ASEAN Trade in Goods Agreement, shortName, ATIGA]
Generated description
ATIGA is a key ASEAN agreement that aims to liberalize and facilitate trade in goods among member states by reducing tariffs and harmonizing trade rules.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ATIGA
Target entity description: ATIGA is a key ASEAN agreement that aims to liberalize and facilitate trade in goods among member states by reducing tariffs and harmonizing trade rules.
  • A. ATIA
    ATIA is the commonly used acronym for Canada’s federal Access to Information Act, which grants the public a legal right to access government records.
  • B. Atiim
    Atiim is the given first name of former NFL running back and sports media personality Tiki Barber.
  • C. Atadage
    Atadage is an ancient stone temple in the medieval Sri Lankan city of Polonnaruwa, believed to have housed the Sacred Tooth Relic of the Buddha.
  • D. AITI
    AITI is an organization known for sponsoring and supporting initiatives related to the Bengali-language internet domain .bn.
  • E. AITI
    AITI is the national regulatory authority overseeing Brunei Darussalam’s information and communications technology (ICT) and telecommunications sectors.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a751e6a08190a42c36722275d5d3 completed April 29, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c82682680819085bc0d9aed83f3e4 completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6f159488190bcde44676ddce593 completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca754878c8190a918fa3b349fd970 completed May 19, 2026, 6:09 p.m.
Created at: April 17, 2026, 6:03 p.m.