Triple
T9120054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Code for Crown Prosecutors |
E218822
|
entity |
| Predicate | firstIssuedInYear |
P51515
|
FINISHED |
| Object | 1986 |
—
|
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: 1986 | Statement: [Code for Crown Prosecutors, firstIssuedInYear, 1986]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstIssuedInYear Context triple: [Code for Crown Prosecutors, firstIssuedInYear, 1986]
-
A.
firstCreationYear
Indicates the year in which something was first created or originally produced.
-
B.
firstReportedYear
Indicates the year in which something was initially reported, documented, or made known for the first time.
-
C.
firstAssociatedPublicationYear
Indicates the calendar year in which an entity’s earliest associated publication was first released or made publicly available.
-
D.
firstVersionYear
chosen
Indicates the calendar year in which the first version or initial release of something was created, published, or made available.
-
E.
firstSeriesYear
Indicates the year in which a series (such as a TV show, book series, or sports league season) first began or was initially released.
- 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_69ca83dddd548190983b96c664f7f367 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8a902e08190a7eb4728f32b9e1d |
completed | April 1, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69cc66003e3c819091e1e42c9cf7c781 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:17 p.m.