Triple
T27325206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew N. Fraser |
E689622
|
entity |
| Predicate | speechAudience |
P74744
|
FINISHED |
| Object | student body at school assembly |
—
|
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: student body at school assembly | Statement: [Matthew N. Fraser, speechAudience, student body at school assembly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speechAudience Context triple: [Matthew N. Fraser, speechAudience, student body at school assembly]
-
A.
audienceDescribedAs
Indicates that an audience is characterized or labeled using a particular description or set of attributes.
-
B.
audienceMember
chosen
Indicates that one entity is an audience member who is attending, observing, or listening to a performance, event, or presentation involving the other entity.
-
C.
speakers
Indicates that one or more entities produce spoken language or vocal communication, typically addressing an audience or participating in a conversation.
-
D.
audienceScale
Indicates the relative size or reach of the audience associated with an entity, event, or communication.
-
E.
audienceRole
Indicates the role or function an entity has as part of an audience in relation to another entity or event.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627ed03ac8190a17ddacba96f8a48 |
completed | May 2, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:35 a.m.