Triple
T14723416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NG-KT |
E345871
|
entity |
| Predicate | identifiesUniquely |
P107472
|
FINISHED |
| Object | Katsina State within Nigeria |
—
|
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: Katsina State within Nigeria | Statement: [NG-KT, identifiesUniquely, Katsina State within Nigeria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: identifiesUniquely Context triple: [NG-KT, identifiesUniquely, Katsina State within Nigeria]
-
A.
typeOfUniqueness
Indicates that one entity’s uniqueness is characterized, classified, or constrained by the specific kind or mode of uniqueness associated with another entity.
-
B.
isUniqueTo
Indicates that a property, characteristic, or association belongs exclusively to a particular entity and is not shared with any other.
-
C.
uniquenessCondition
Indicates that a specified element, value, or combination of attributes must be unique within a given set, context, or domain, with no duplicates allowed.
-
D.
identifiedUsing
chosen
Indicates that one entity was recognized, distinguished, or determined by means of a specified method, tool, or identifier.
-
E.
isUniqueWithinSystem
Indicates that an entity exists only once and has no duplicates within the defined system or scope.
- 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_69d822e5911c8190ba589f957dbd9ba7 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec25e9a14819081fa06fc601f295d |
completed | April 14, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69de657e174481909da0437556334a04 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:29 a.m.