Triple

T15639203
Position Surface form Disambiguated ID Type / Status
Subject University of Karachi E376022 entity
Predicate abbreviation P43 FINISHED
Object KU E376022 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: KU | Statement: [University of Karachi, abbreviation, KU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KU
Context triple: [University of Karachi, abbreviation, KU]
  • A. KU
    KU is a common abbreviation for Kyoto University, a prestigious national research university in Kyoto, Japan.
  • B. KU chosen
    KU is a common abbreviation for the University of Karachi, a major public research university in Karachi, Pakistan.
  • C. KU
    KU is the commonly used abbreviation for Kutztown University of Pennsylvania, a public university located in Kutztown, Pennsylvania.
  • D. KU
    KU is the commonly used abbreviation for the University of Kashmir, a major public university located in Srinagar, Jammu and Kashmir, India.
  • E. KU
    KU is the University of Kansas, a major public research university in Lawrence, Kansas, known for its strong athletics and distinctive school traditions.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ed06b388190bfebb77fe70e7df1 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f4b693c81908fd324a5e92fc23c completed May 9, 2026, 4:22 p.m.
Created at: April 10, 2026, 4:14 a.m.