Triple

T17458395
Position Surface form Disambiguated ID Type / Status
Subject Aircalin E425089 entity
Predicate ICAOcode P419 FINISHED
Object ACI
ACI is the ICAO airline designator assigned to Aircalin, the international airline of New Caledonia.
E1270620 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: ACI | Statement: [Aircalin, ICAOcode, ACI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ACI
Context triple: [Aircalin, ICAOcode, ACI]
  • A. ACI
    ACI is Cisco's software-defined networking solution that provides centralized, policy-based automation and management for data center networks.
  • B. ACI Europe
    ACI Europe is the trade association representing European airports, advocating for their interests and promoting safe, efficient, and sustainable air transport across Europe.
  • C. ACIA
    ACIA is a key ASEAN agreement designed to liberalize, protect, and promote investment among member states to foster regional economic integration.
  • D. ACSI
    ACSI is Atari's proprietary hard disk and peripheral interface standard used to connect external storage devices to its computers.
  • E. AICS
    AICS is the Allen Institute for Cell Science, a research organization focused on understanding and modeling the structure and behavior of human cells.
  • 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: ACI
Triple: [Aircalin, ICAOcode, ACI]
Generated description
ACI is the ICAO airline designator assigned to Aircalin, the international airline of New Caledonia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ACI
Target entity description: ACI is the ICAO airline designator assigned to Aircalin, the international airline of New Caledonia.
  • A. ACI
    ACI is Cisco's software-defined networking solution that provides centralized, policy-based automation and management for data center networks.
  • B. ACI Europe
    ACI Europe is the trade association representing European airports, advocating for their interests and promoting safe, efficient, and sustainable air transport across Europe.
  • C. ACIA
    ACIA is a key ASEAN agreement designed to liberalize, protect, and promote investment among member states to foster regional economic integration.
  • D. ACSI
    ACSI is Atari's proprietary hard disk and peripheral interface standard used to connect external storage devices to its computers.
  • E. AICS
    AICS is the Allen Institute for Cell Science, a research organization focused on understanding and modeling the structure and behavior of human cells.
  • 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_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4514385e48190b97a257bb3d07d2d completed April 19, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01b820024c8190bd8f083b426f82f5 completed May 11, 2026, 11:06 a.m.
NEDg Description generation batch_6a01b90e68d08190be86aee8d6692ce1 completed May 11, 2026, 11:10 a.m.
NED2 Entity disambiguation (via description) batch_6a01b993324081908b561700bbeac11c completed May 11, 2026, 11:12 a.m.
Created at: April 10, 2026, 5:47 a.m.