Triple

T17076121
Position Surface form Disambiguated ID Type / Status
Subject 3i Group E414351 entity
Predicate abbreviation P43 FINISHED
Object 3i E644853 NE 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: 3i | Statement: [3i Group, abbreviation, 3i]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 3i
Context triple: [3i Group, abbreviation, 3i]
  • A. 3i chosen
    3i is a leading international private equity and venture capital firm based in the United Kingdom, known for investing in and acquiring growth-oriented businesses across various sectors.
  • B. I3
    I3 is the IATA airline designator formerly assigned to ATA Airlines, a now-defunct U.S. low-cost carrier.
  • C. S-I
    S-I was the first-stage booster of NASA’s early Saturn I launch vehicle, providing the initial thrust for some of the United States’ first heavy-lift test flights in the Apollo era.
  • D. I3A
    I3A is a global trade association representing companies and organizations involved in the imaging and photographic technology industry.
  • E. Si
    Si is one of the mischievous Siamese cats from Disney’s animated film "Lady and the Tramp," known for causing trouble with her twin, Am.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbc559388190b685504cca6ed62b completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012edfda588190aff6c6d4c8d64ddd completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:34 a.m.