Triple

T15030529
Position Surface form Disambiguated ID Type / Status
Subject Victim Compensation Formula Grants E378330 entity
Predicate jurisdiction P82 FINISHED
Object U.S. states E87403 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: U.S. states | Statement: [Victim Compensation Formula Grants, jurisdiction, U.S. states]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: U.S. states
Context triple: [Victim Compensation Formula Grants, jurisdiction, U.S. states]
  • A. U.S. states chosen
    U.S. states are the 50 constituent political entities that share sovereignty with the federal government of the United States, each with its own constitution, laws, and governance structure.
  • B. States
    States are the primary constituent political units of the Republic of India, each with its own government and legislature operating within the federal constitutional framework.
  • C. States
    The States are the individual self-governing regional political units within the federal system of Australia, each with its own parliament and constitutional powers.
  • D. Stathe
    Stathe is a small village in Somerset, England, situated close to the River Parrett on the Somerset Levels.
  • E. État
    État is a French public transport ticketing system used for accessing and paying for services across the national rail and associated networks.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e2416081908dfba48d7f7b4a84 completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9ddb46888190b1d2fe2992fc120b completed May 9, 2026, 2:37 a.m.
Created at: April 10, 2026, 2:59 a.m.