Triple
T21227109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3GPP TS 23-series |
E523111
|
entity |
| Predicate | usesSpecificationType |
P45345
|
FINISHED |
| Object | stage 2 specification |
—
|
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: stage 2 specification | Statement: [3GPP TS 23-series, usesSpecificationType, stage 2 specification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSpecificationType Context triple: [3GPP TS 23-series, usesSpecificationType, stage 2 specification]
-
A.
hasSpecification
Indicates that an entity is associated with a particular specification that defines or constrains its properties, behavior, or requirements.
-
B.
specType
chosen
Indicates the specific type or category of a specification that an entity is associated with.
-
C.
usesSpecEngine
Indicates that one entity employs or relies on a specific engine as its underlying mechanism or processing component.
-
D.
specifiedFor
Indicates that something is designated or intended to be used for a particular entity, purpose, or context.
-
E.
usesToolType
Indicates that an entity performs an action or fulfills a role by employing a specific type or category of tool.
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734ac42a08190b95a24acf5f0779b |
completed | April 21, 2026, 8:26 a.m. |
| PD | Predicate disambiguation | batch_69e5f60e1a888190ba75e2e900270a4e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:44 p.m.