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.