Triple

T10948219
Position Surface form Disambiguated ID Type / Status
Subject Panzergrenadier-Regiment 104 E258651 entity
Predicate hasUnitTypeCharacteristic P274 FINISHED
Object combined arms cooperation with tanks 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: combined arms cooperation with tanks | Statement: [Panzergrenadier-Regiment 104, hasUnitTypeCharacteristic, combined arms cooperation with tanks]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasUnitTypeCharacteristic
Context triple: [Panzergrenadier-Regiment 104, hasUnitTypeCharacteristic, combined arms cooperation with tanks]
  • A. hasUnitOf
    Indicates that a quantity, measurement, or value is expressed in terms of a specific unit.
  • B. basedUnitType
    Indicates that one unit is defined or derived in terms of another underlying (base) unit type.
  • C. hasCharacteristic chosen
    Indicates that an entity possesses, exhibits, or is defined by a particular attribute, feature, or quality.
  • D. hasBasicUnit
    Indicates that one entity is composed of, defined by, or fundamentally characterized through another entity that serves as its basic or minimal unit.
  • E. typeOfUnit
    Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
  • 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770ebac3c8190849ddda3d9d37327 completed April 9, 2026, 9:27 a.m.
PD Predicate disambiguation batch_69d72e816a98819096d6c10dfb88a66a completed April 9, 2026, 4:43 a.m.
Created at: April 8, 2026, 9:23 p.m.