Triple

T19518895
Position Surface form Disambiguated ID Type / Status
Subject Taro Island E488352 entity
Predicate airportICAOcode P419 FINISHED
Object AGGC
AGGC is the ICAO airport code for Taro Island Airport in the Solomon Islands.
 E1379739 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: AGGC | Statement: [Taro Island, airportICAOcode, AGGC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AGGC
Context triple: [Taro Island, airportICAOcode, AGGC]
  • A. AGTC
    AGTC is a United Nations economic commission agreement that defines and coordinates key international combined (multimodal) transport routes and related infrastructure across Europe.
  • B. AGG
    AGG is a high-quality, open-source 2D graphics rendering library known for its precision and anti-aliasing capabilities.
  • C. GGC
    GGC is a public four-year college in Lawrenceville, Georgia, known for its open-access mission and rapidly growing, diverse student body.
  • D. GGC
    GGC is the abbreviation for the Gulf of Guinea Commission, a regional organization that promotes cooperation and security among states bordering the Gulf of Guinea in West and Central Africa.
  • E. AGAT
    AGAT is a Polish special forces unit known for high-risk direct action, counterterrorism, and rapid response operations.
  • 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: AGGC
Triple: [Taro Island, airportICAOcode, AGGC]
Generated description
AGGC is the ICAO airport code for Taro Island Airport in the Solomon Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AGGC
Target entity description: AGGC is the ICAO airport code for Taro Island Airport in the Solomon Islands.
  • A. AGTC
    AGTC is a United Nations economic commission agreement that defines and coordinates key international combined (multimodal) transport routes and related infrastructure across Europe.
  • B. AGG
    AGG is a high-quality, open-source 2D graphics rendering library known for its precision and anti-aliasing capabilities.
  • C. GGC
    GGC is a public four-year college in Lawrenceville, Georgia, known for its open-access mission and rapidly growing, diverse student body.
  • D. GGC
    GGC is the abbreviation for the Gulf of Guinea Commission, a regional organization that promotes cooperation and security among states bordering the Gulf of Guinea in West and Central Africa.
  • E. AGAT
    AGAT is a Polish special forces unit known for high-risk direct action, counterterrorism, and rapid response operations.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6359edd508190afd68739de676ed7 completed April 20, 2026, 2:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a074728f7548190a6a8e1888e8c8180 completed May 15, 2026, 4:17 p.m.
NEDg Description generation batch_6a07483465008190966296ddca76e7d2 completed May 15, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_6a074931b1dc8190804d545e2058a69a completed May 15, 2026, 4:26 p.m.
Created at: April 10, 2026, 1:40 p.m.