Triple

T25148755
Position Surface form Disambiguated ID Type / Status
Subject TED Talk "Designing books is no laughing matter. OK, it is." E630011 entity
Predicate speakerName P90848 FINISHED
Object Chip Kidd NE NERFINISHED

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: Chip Kidd | Statement: [TED Talk "Designing books is no laughing matter. OK, it is.", speakerName, Chip Kidd]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: speakerName
Context triple: [TED Talk "Designing books is no laughing matter. OK, it is.", speakerName, Chip Kidd]
  • A. speakerMP
    Indicates that the subject is a Member of Parliament who holds or is identified with the role of Speaker (or a speaker-related parliamentary position).
  • B. speakerInText chosen
    Indicates that a given entity is the person who speaks or is quoted within a particular text or textual segment.
  • C. speechAlsoKnownAs
    Indicates that a speech or spoken work is referred to by an alternative name, title, or alias.
  • D. speakerType
    Indicates the role or category of a participant in a communicative act (e.g., narrator, quoted speaker, system voice) within a given context.
  • E. identifiesSpeakerAs
    Indicates that one entity designates or recognizes another entity as the speaker of a given utterance or communication.
  • 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_69e2ff349e408190a6f4a5a66279f54d completed April 18, 2026, 3:49 a.m.
NER Named-entity recognition batch_69f4684f11708190aa73600e3367475b completed May 1, 2026, 8:46 a.m.
PD Predicate disambiguation batch_69f45cfb53f4819099bba48c5057e787 completed May 1, 2026, 7:57 a.m.
Created at: April 18, 2026, 6:30 a.m.