Triple
T31995620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Youth Justice and Criminal Evidence Act 1999 |
E816984
|
entity |
| Predicate | sectionIntroduces |
P83636
|
FINISHED |
| Object | special measures directions for eligible witnesses |
—
|
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: special measures directions for eligible witnesses | Statement: [Youth Justice and Criminal Evidence Act 1999, sectionIntroduces, special measures directions for eligible witnesses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectionIntroduces Context triple: [Youth Justice and Criminal Evidence Act 1999, sectionIntroduces, special measures directions for eligible witnesses]
-
A.
sectionIntroduced
chosen
Indicates that a particular section was introduced or added at a specific point in time or context.
-
B.
sectionPurpose
Indicates that a section exists for the purpose of fulfilling or serving a specified function, role, or intended use.
-
C.
sectionProvided
Indicates that a specific section or portion of content has been supplied or made available by one entity to another.
-
D.
section
Indicates that one entity is a distinct part, division, or segment of another entity within a larger whole.
-
E.
secondIntroduction
Indicates that an entity is being introduced or presented for the second time in a given context or sequence.
- 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_69f348f8002081909a3588758ba94afb |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b3f782788190aa4b2dfa9e6eab19 |
completed | May 3, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:13 a.m.