Triple
T26237048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catholic Church in Portugal |
E656200
|
entity |
| Predicate | operatesUniversity |
P33435
|
FINISHED |
| Object | Catholic University of Portugal |
—
|
NE NERFINISHED |
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: Catholic University of Portugal | Statement: [Catholic Church in Portugal, operatesUniversity, Catholic University of Portugal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesUniversity Context triple: [Catholic Church in Portugal, operatesUniversity, Catholic University of Portugal]
-
A.
operatesInstitution
chosen
Indicates that an entity manages and runs the activities or services of an institution.
-
B.
university2
Indicates a relationship where an entity is a university associated with, attended by, or otherwise linked to another entity.
-
C.
campusSystem
Indicates a relationship where an educational institution is part of, managed by, or operates within a particular campus system or network.
-
D.
publicUniversityCampus
Indicates that a university campus is publicly funded or state-operated rather than privately owned.
-
E.
university
Indicates that an educational institution of higher learning is associated with or attended by a given entity.
- 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_69ee5b4b8b408190993da38c0067cc8d |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69fcda3699948190adb57625bae08091 |
completed | May 7, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fd16d08190b0aca6e19a632e99 |
completed | May 7, 2026, 6:25 p.m. |
Created at: April 26, 2026, 9:02 p.m.