Triple

T4615815
Position Surface form Disambiguated ID Type / Status
Subject Air India E100865 entity
Predicate ICAOCode P419 FINISHED
Object AIC
AIC is the ICAO airline designator used to identify Air India in international aviation operations and communications.
 E458478 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: AIC | Statement: [Air India, ICAOCode, AIC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AIC
Context triple: [Air India, ICAOCode, AIC]
  • A. AICS
    AICS is the Allen Institute for Cell Science, a research organization focused on understanding and modeling the structure and behavior of human cells.
  • B. AICUM
    AICUM is an academic or research-related organization associated with George Washington University.
  • C. AICUM
    AICUM is a nonprofit advocacy organization representing the interests of private, independent colleges and universities in Massachusetts.
  • D. AIB
    AIB is the Smithsonian Institution’s historic Arts and Industries Building in Washington, D.C., known as one of the oldest museum buildings on the National Mall.
  • E. A3C
    A3C (Asynchronous Advantage Actor-Critic) is a reinforcement learning algorithm that trains multiple parallel agents to learn policies and value functions efficiently using asynchronous gradient updates.
  • 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: AIC
Triple: [Air India, ICAOCode, AIC]
Generated description
AIC is the ICAO airline designator used to identify Air India in international aviation operations and communications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AIC
Target entity description: AIC is the ICAO airline designator used to identify Air India in international aviation operations and communications.
  • A. AICS
    AICS is the Allen Institute for Cell Science, a research organization focused on understanding and modeling the structure and behavior of human cells.
  • B. AICUM
    AICUM is an academic or research-related organization associated with George Washington University.
  • C. AICUM
    AICUM is a nonprofit advocacy organization representing the interests of private, independent colleges and universities in Massachusetts.
  • D. AIB
    AIB is the Smithsonian Institution’s historic Arts and Industries Building in Washington, D.C., known as one of the oldest museum buildings on the National Mall.
  • E. A3C
    A3C (Asynchronous Advantage Actor-Critic) is a reinforcement learning algorithm that trains multiple parallel agents to learn policies and value functions efficiently using asynchronous gradient updates.
  • 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_69bd43cf363c819087fd5ab441b4a3f4 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd59df3c3c8190be5db000f831d322 completed March 20, 2026, 2:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa8da23881909ba4a70e9697f260 completed March 21, 2026, 1:55 a.m.
NEDg Description generation batch_69bdfc7b84108190af39c7780f702745 completed March 21, 2026, 2:03 a.m.
NED2 Entity disambiguation (via description) batch_69bdfd3856b48190a44f49da5fde38f6 completed March 21, 2026, 2:06 a.m.
Created at: March 20, 2026, 1:12 p.m.