Triple
T36470396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diocese of São Tomé and Príncipe |
E898524
|
entity |
| Predicate | countryCapitalInDiocese |
P203855
|
FINISHED |
| Object | São Tomé |
E134456
|
NE 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: São Tomé | Statement: [Diocese of São Tomé and Príncipe, countryCapitalInDiocese, São Tomé]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryCapitalInDiocese Context triple: [Diocese of São Tomé and Príncipe, countryCapitalInDiocese, São Tomé]
-
A.
isDiocesanSeatOf
Indicates that a location serves as the central administrative seat or headquarters of a particular diocese.
-
B.
isArchdioceseSeatOf
Indicates that a particular archdiocese serves as the central ecclesiastical jurisdiction and administrative seat for a specified church region or authority.
-
C.
countryCapitalCityCathedral
chosen
Indicates that a cathedral is located in the capital city of a given country.
-
D.
dioceseGovernedStart
Indicates the point in time when a particular authority or leader began governing a specific diocese.
-
E.
administrativeDiocese
Indicates that one entity serves as the ecclesiastical administrative diocese responsible for the governance or oversight of another entity.
- F. None of above.
Provenance (4 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_69f76e58ebd88190b75d9b169b59d793 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0309a4e4d481908a6070b40d507aae |
completed | May 12, 2026, 11:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39e6d0cfd08190a1d959c3eac0df2a |
completed | June 23, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_6a03091ac1008190bf50357364d4e9e4 |
completed | May 12, 2026, 11:03 a.m. |
Created at: May 3, 2026, 4:10 p.m.