Triple

T15962712
Position Surface form Disambiguated ID Type / Status
Subject University of Tunis E387101 entity
Predicate abbreviation P43 FINISHED
Object UT E387101 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: UT | Statement: [University of Tunis, abbreviation, UT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UT
Context triple: [University of Tunis, abbreviation, UT]
  • A. UT
    UT is the IATA airline designator assigned to UTair Aviation, a Russian airline.
  • B. UT chosen
    UT is the common abbreviation for the University of Tunis, a major public university in Tunisia’s capital city.
  • C. UT
    UT is the official two-letter United States Postal Service abbreviation for the state of Utah.
  • D. UT
    UT is the common abbreviation for the University of Tours, a French public university located in the city of Tours.
  • E. UT
    UT is the commonly used abbreviation for the University of Tehran, Iran’s oldest and most prestigious modern university.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157013cfc819099fa83de85273710 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe827d248190adbfd41f55638ebd completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:53 a.m.