Triple
T21981300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OS Explorer OL4 |
E542845
|
entity |
| Predicate | productCodeType |
P145090
|
FINISHED |
| Object | OL series number |
—
|
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: OL series number | Statement: [OS Explorer OL4, productCodeType, OL series number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productCodeType Context triple: [OS Explorer OL4, productCodeType, OL series number]
-
A.
catalogCode
Indicates that an entity is assigned a specific catalog identifier or code used for classification or reference.
-
B.
productionCode
Indicates the unique identifier or code assigned to a specific production (such as a film, TV episode, or manufactured item) that links related records or versions of that production.
-
C.
manufacturerCode
Indicates the unique code assigned by a manufacturer to identify a specific product, component, or item it produces.
-
D.
platformCode
Indicates the specific code or identifier assigned to a platform (such as a station platform or service platform) associated with the subject entity.
-
E.
seriesCode
chosen
Indicates that an entity is assigned a specific code identifying the series or collection to which it belongs.
- 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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1248de3688190a8d24cc8458851f2 |
completed | April 28, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:04 p.m.