Triple

T12514713
Position Surface form Disambiguated ID Type / Status
Subject GNU As E299165 entity
Predicate supportsTarget P5090 FINISHED
Object PRU E74088 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: PRU | Statement: [GNU As, supportsTarget, PRU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PRU
Context triple: [GNU As, supportsTarget, PRU]
  • A. PRU chosen
    PRU is the stock ticker symbol for Prudential Financial, a major U.S.-based financial services and insurance company.
  • B. PR-2
    PR-2 is a major highway in Puerto Rico that runs along much of the island’s northern and western coasts, connecting several key cities and regions.
  • C. PRR
    PRR is the abbreviation commonly used for the Pennsylvania Railroad Company, once one of the largest and most influential railroads in the United States.
  • D. PRR
    PRR is a set of UK financial regulations governing the content and approval of prospectuses for securities offerings to protect investors and ensure market transparency.
  • E. LKPR
    LKPR is the ICAO airport code for Václav Havel Airport Prague, the main international airport serving Prague and the Czech Republic.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9541e752c8190bf12d2b5a37b53df completed April 10, 2026, 7:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bbd58b88190baeb99380babf64f completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.