Triple

T14776639
Position Surface form Disambiguated ID Type / Status
Subject Madam Chairman E347277 entity
Predicate speechActType P29536 FINISHED
Object vocative expression 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: vocative expression | Statement: [Madam Chairman, speechActType, vocative expression]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: speechActType
Context triple: [Madam Chairman, speechActType, vocative expression]
  • A. speechAct
    Indicates that one entity performs a communicative action (such as stating, asking, commanding, or promising) directed toward another entity or audience.
  • B. speechType chosen
    Indicates the specific category or form of spoken or written communication that an utterance or speech act belongs to (e.g., question, statement, command).
  • C. typeOfSpeechDelivered
    Indicates that a specific kind or category of speech (e.g., keynote, lecture, toast) was delivered in a given event or context.
  • D. dialogueType
    Indicates the specific kind or category of dialogue occurring between entities (e.g., question-answer, negotiation, instruction).
  • E. dialogueAction
    Indicates an action performed within a dialogue or conversation between entities, such as speaking, asking, answering, or otherwise verbally interacting.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec817c39081909b08a0ffdfce9936 completed April 14, 2026, 11:04 p.m.
PD Predicate disambiguation batch_69de8c02e5c08190943c27594026faf7 completed April 14, 2026, 6:48 p.m.
Created at: April 10, 2026, 1:31 a.m.