Triple
T36443253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Court in Sabah and Sarawak |
E897794
|
entity |
| Predicate | hasAdditionalRegistriesIn |
P89056
|
FINISHED |
| Object | other towns in Sabah |
—
|
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: other towns in Sabah | Statement: [High Court in Sabah and Sarawak, hasAdditionalRegistriesIn, other towns in Sabah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdditionalRegistriesIn Context triple: [High Court in Sabah and Sarawak, hasAdditionalRegistriesIn, other towns in Sabah]
-
A.
hasDistrictRegistries
chosen
Indicates that an entity maintains or is associated with one or more official registries at the district level.
-
B.
hasRegistryView
Indicates that an entity has permission or capability to access and view a particular registry or registry-related information.
-
C.
hasAdditionalCollection
Indicates that one entity possesses or is associated with an extra or supplementary collection beyond its primary collection.
-
D.
hasRegistrar
Indicates that an entity is formally recorded or overseen by a specific registrar organization or authority.
-
E.
belongsToRegistry
Indicates that an entity is officially recorded as part of a specific registry or registered collection.
- 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_69f76e5720b481908f8177ac24a7560b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe21b0cba48190b56c39e9f1c0eafa |
completed | May 8, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69fe204576848190aecf204e2adba5dc |
completed | May 8, 2026, 5:41 p.m. |
Created at: May 3, 2026, 4:10 p.m.