Triple

T33762539
Position Surface form Disambiguated ID Type / Status
Subject Apocryphon: Electro Roots 1982–1985 E865149 entity
Predicate featuresEarlyRecordingsOf P86042 FINISHED
Object Information Society E246875 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: Information Society | Statement: [Apocryphon: Electro Roots 1982–1985, featuresEarlyRecordingsOf, Information Society]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: featuresEarlyRecordingsOf
Context triple: [Apocryphon: Electro Roots 1982–1985, featuresEarlyRecordingsOf, Information Society]
  • A. containsEarlyBandRecordings chosen
    Indicates that something includes recordings made by a band during its early period or formative years.
  • B. recordingsKnownAs
    Indicates that one recording is known, referred to, or identified by a particular alternative name or title.
  • C. firstRecordedWith
    Indicates that an entity’s earliest known or documented occurrence is associated with a specified context, source, or accompanying entity.
  • D. recordingsFrom
    Indicates a relationship where one entity serves as the source or origin of recordings that are associated with or derived from it.
  • E. oftenRecordedIn
    Indicates that instances of one entity are frequently documented, logged, or captured within another entity (such as a medium, dataset, or record).
  • F. None of above.

Provenance (4 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_69f3498d3b748190aa3c4006c1f32f38 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_6a02145017b08190bd424cc647c08d3b completed May 11, 2026, 5:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3872607284819086f49208a9338bf1 completed June 21, 2026, 11:23 p.m.
PD Predicate disambiguation batch_6a021338e2b08190980c489ee44c18b3 completed May 11, 2026, 5:34 p.m.
Created at: May 1, 2026, 1:45 a.m.