Triple
T12964988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IELTS |
E321237
|
entity |
| Predicate | speakingFormat |
P130
|
FINISHED |
| Object | face-to-face interview |
—
|
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: face-to-face interview | Statement: [IELTS, speakingFormat, face-to-face interview]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speakingFormat Context triple: [IELTS, speakingFormat, face-to-face interview]
-
A.
dialogueFormat
Indicates the specific structure or style in which a dialogue or conversational exchange is presented or encoded between entities.
-
B.
speechType
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.
format
chosen
Indicates the specific arrangement, structure, or presentation style in which something is organized or expressed.
-
D.
portrayalFormat
Indicates the medium or format in which something is portrayed or represented (e.g., painting, sculpture, film, digital).
-
E.
speakerType
Indicates the role or category of a participant in a communicative act (e.g., narrator, quoted speaker, system voice) within a given context.
- 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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97dba57988190b786ffed55687a72 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 8:27 p.m.