Triple

T13601970
Position Surface form Disambiguated ID Type / Status
Subject MDCT E324964 entity
Predicate typicalBlockStructure P17710 FINISHED
Object even-length blocks with 50% overlap 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: even-length blocks with 50% overlap | Statement: [MDCT, typicalBlockStructure, even-length blocks with 50% overlap]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalBlockStructure
Context triple: [MDCT, typicalBlockStructure, even-length blocks with 50% overlap]
  • A. commonStructure
    Indicates that two or more entities share the same or a very similar internal organization, pattern, or arrangement.
  • B. typicalStructuralElement
    Indicates that one entity is a standard or characteristic structural component commonly found within or forming part of another entity.
  • C. textualStructure
    Indicates how parts of a text are organized and related to each other within its overall structure.
  • D. traditionalStructure
    Indicates that something follows or embodies a customary, historically established form, pattern, or organizational framework.
  • E. segmentStructure chosen
    Indicates that one entity represents a structural or organizational subdivision (a segment) within the overall structure of another entity.
  • 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_69d80769eaf081909d82f44e484d6113 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb07ad3f48190a2173e42c5cfedb1 completed April 12, 2026, 2:47 p.m.
PD Predicate disambiguation batch_69dbae18eaf48190809e8b365856cde9 completed April 12, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:49 p.m.