Triple
T20743003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Church Going |
E510491
|
entity |
| Predicate | speakerDescription |
P40912
|
FINISHED |
| Object | skeptical but curious visitor |
—
|
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: skeptical but curious visitor | Statement: [Church Going, speakerDescription, skeptical but curious visitor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speakerDescription Context triple: [Church Going, speakerDescription, skeptical but curious visitor]
-
A.
speakerType
Indicates the role or category of a participant in a communicative act (e.g., narrator, quoted speaker, system voice) within a given context.
-
B.
speakerRole
Indicates the functional role or capacity in which an entity is acting as a speaker within a communicative event.
-
C.
speakerFeatures
chosen
Indicates that certain characteristics, attributes, or properties are associated with a speaker in a given context.
-
D.
speakerInText
Indicates that a given entity is the person who speaks or is quoted within a particular text or textual segment.
-
E.
speaker2
Indicates that the referenced entity serves as the second speaker or interlocutor in a communicative interaction or dialogue.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c210a2c08190bd767df3188bb401 |
completed | April 21, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c0509608819080cdbf47fcddfe36 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:33 p.m.