Triple

T18749232
Position Surface form Disambiguated ID Type / Status
Subject Flying Returns E458481 entity
Predicate programTarget P133401 FINISHED
Object retention of Air India customers LITERAL FINISHED

How this triple was built (2 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: retention of Air India customers | Statement: [Flying Returns, programTarget, retention of Air India customers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: programTarget
Context triple: [Flying Returns, programTarget, retention of Air India customers]
  • A. program
    Indicates that an entity creates, writes, or develops a computer program or software application.
  • B. intendedProgram
    Indicates the academic or training program that an entity plans or expects to pursue, rather than one they are currently enrolled in or have completed.
  • C. plannedTarget
    Indicates that one entity has been designated or selected as the intended target or objective of another entity’s planned action or operation.
  • D. backendTarget
    Indicates that one entity serves as the backend system, service, or endpoint that another entity connects to or depends on for processing or functionality.
  • E. componentProgram
    Indicates that one entity is a component or module that forms part of a larger program or software system represented by the other entity.
  • F. None of above. chosen

Provenance (4 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e579eb7350819099d7291207781116 completed April 20, 2026, 12:57 a.m.
PD Predicate disambiguation batch_69e48d0b7b708190877951b6e6cdcbc4 completed April 19, 2026, 8:06 a.m.
PDg Predicate description generation batch_69e49a9bcc0c81908df3e513fd6762ff completed April 19, 2026, 9:04 a.m.
Created at: April 10, 2026, 11:51 a.m.