Triple
T4583023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saville Inquiry |
E101897
|
entity |
| Predicate | evidenceCollected |
P9384
|
FINISHED |
| Object | thousands of witness statements |
—
|
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: thousands of witness statements | Statement: [Saville Inquiry, evidenceCollected, thousands of witness statements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evidenceCollected Context triple: [Saville Inquiry, evidenceCollected, thousands of witness statements]
-
A.
providesEvidenceFor
Indicates that one entity serves as support, justification, or proof for the validity or truth of another entity.
-
B.
usedEvidenceType
Indicates that a particular type or category of evidence was employed or relied upon in a given context or activity.
-
C.
collectedThrough
chosen
Indicates that something was obtained, gathered, or acquired by means of a specified process, method, or channel.
-
D.
investigatedBy
Indicates that an entity is the subject of an investigation carried out by another entity.
-
E.
hasNoEvidenceOf
Indicates that there is no supporting proof, data, or documentation confirming the existence or occurrence of the referenced condition, event, or relationship.
- 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_69bd43d4ce208190b53158c882b222e3 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59029568819091db1e77a9a2ec41 |
completed | March 20, 2026, 2:26 p.m. |
| PD | Predicate disambiguation | batch_69bd522acbcc8190bf24d9517793a2c1 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:10 p.m.