Triple

T20139403
Position Surface form Disambiguated ID Type / Status
Subject CTI E491118 entity
Predicate abbreviation P43 FINISHED
Object CTI NE NERFINISHED

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: CTI | Statement: [CTI, abbreviation, CTI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CTI
Context triple: [CTI, abbreviation, CTI]
  • A. CTI chosen
    CTI is the French national accreditation body responsible for evaluating and authorizing engineering degree programs.
  • B. CTI
    CTI is the abbreviation for APEC’s Committee on Trade and Investment, a body that works to advance regional trade and investment liberalization and facilitation among member economies.
  • C. CTIIC
    CTIIC is a U.S. government center responsible for integrating, analyzing, and coordinating cyber threat intelligence across federal agencies.
  • D. CTIA
    CTIA is an early custom video display chip used in Atari 8-bit computers to generate their on-screen graphics and color output.
  • E. CTI-CFF
    CTI-CFF is a multilateral regional partnership among Coral Triangle countries focused on conserving marine and coastal resources to sustain fisheries, biodiversity, and food security.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667698a188190869c18b925dba2ed completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:32 p.m.