Triple
T2102830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strange Meeting |
E37128
|
entity |
| Predicate | speaker1 |
P29800
|
FINISHED |
| Object | British soldier |
—
|
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: British soldier | Statement: [Strange Meeting, speaker1, British soldier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speaker1 Context triple: [Strange Meeting, speaker1, British soldier]
-
A.
typicalSpeaker
Indicates that the subject is a prototypical or characteristic speaker or source of utterances in the context of the object.
-
B.
speakerType
chosen
Indicates the role or category of a participant in a communicative act (e.g., narrator, quoted speaker, system voice) within a given context.
-
C.
spokenOn
Indicates that an utterance or speech act occurred at or during a specific time or date.
-
D.
holder
Indicates that one entity possesses, controls, or has custody of another entity, typically in a temporary or contextual sense.
-
E.
spokenAlong
Indicates that two or more languages are used concurrently or within the same context in a particular place, time, or situation.
- 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_69a8861828948190924aa30c08806b3a |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abbabe1e9081908ea66c5406e2f1d9 |
completed | March 7, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69abb7b7b6288190afa11b4d93bd5666 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.