Triple

T26228875
Position Surface form Disambiguated ID Type / Status
Subject Danilo I Petrović-Njegoš E655971 entity
Predicate previousGovernmentForm P86110 FINISHED
Object theocratic bishopric LITERAL 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: theocratic bishopric | Statement: [Danilo I Petrović-Njegoš, previousGovernmentForm, theocratic bishopric]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousGovernmentForm
Context triple: [Danilo I Petrović-Njegoš, previousGovernmentForm, theocratic bishopric]
  • A. governmentFormBefore chosen
    Indicates that one form of government existed prior to another form of government in a temporal sequence.
  • B. governmentFormModeled
    Indicates that one government form is modeled after, or structurally based on, another government form.
  • C. formsGovernment
    Indicates that an entity establishes and assumes control of a governing body or administration for a political unit.
  • D. governmentFormUnder
    Indicates that one governmental form or system operates under the authority, framework, or jurisdiction of another governmental form.
  • E. governmentFormDuring
    Indicates the form or type of government that was in place during a specified time period or event.
  • F. None of above.

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_69ee5b4b8b408190993da38c0067cc8d completed April 26, 2026, 6:36 p.m.
NER Named-entity recognition batch_69f75dc25fa08190b371faf36d9fb72c completed May 3, 2026, 2:37 p.m.
PD Predicate disambiguation batch_69f758586534819083e91172f4bf5098 completed May 3, 2026, 2:14 p.m.
Created at: April 26, 2026, 8:59 p.m.