Triple
T18344993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISO 3166-2:ST |
E439512
|
entity |
| Predicate | territorialSubdivision |
P766
|
FINISHED |
| Object | island of São Tomé |
—
|
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: island of São Tomé | Statement: [ISO 3166-2:ST, territorialSubdivision, island of São Tomé]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territorialSubdivision Context triple: [ISO 3166-2:ST, territorialSubdivision, island of São Tomé]
-
A.
realmSubdivision
Indicates a hierarchical relationship where one realm is a constituent subdivision or part of a larger realm.
-
B.
countrySubdivision
chosen
Indicates that one geopolitical region is an administrative or territorial subdivision of a larger country.
-
C.
governingSubdivision
Indicates that one administrative or political unit serves as the governing authority over a smaller, subordinate territorial subdivision.
-
D.
countrySubdivisionType
Indicates the specific type or category of an administrative or territorial subdivision within a country (e.g., state, province, region).
-
E.
partOfCountrySubdivision
Indicates that one geographic or administrative unit is contained within and forms a component part of a larger country subdivision.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f3bb888190bdeea4c4d114a43b |
completed | April 19, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.