Triple
T37436665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cristóbal López Romero |
E930291
|
entity |
| Predicate | countryOfArchdiocese |
P144143
|
FINISHED |
| Object | Morocco |
E7408
|
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: Morocco | Statement: [Cristóbal López Romero, countryOfArchdiocese, Morocco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfArchdiocese Context triple: [Cristóbal López Romero, countryOfArchdiocese, Morocco]
-
A.
ecclesiasticalCountry
Indicates that a country is associated with or governed by a particular ecclesiastical (church) jurisdiction or authority.
-
B.
countryOfTitularChurch
Indicates the country in which a given titular church is geographically located.
-
C.
hasArchdiocese
Indicates that an entity serves as the archdiocese (ecclesiastical jurisdiction) associated with another entity, such as a church, region, or religious organization.
-
D.
countryOfBishopric
chosen
Indicates the country in which a given bishopric (episcopal see or diocese) is located or to which it belongs.
-
E.
continentOfDiocese
Indicates that a diocese is located on, or belongs geographically to, a specific continent.
- 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_69f76ebfdcb8819098562ff3db673b04 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0361c6d76481909332b28ab01b0ef7 |
completed | May 12, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a408c2a4850819098b005e1a3f63111 |
completed | June 28, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_6a0360b3818c819084bbecf705475f4f |
completed | May 12, 2026, 5:17 p.m. |
Created at: May 3, 2026, 4:17 p.m.