Triple
T30654747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ley sobre Libertad de Cultos |
E780354
|
entity |
| Predicate | grupoAfectado |
P10927
|
FINISHED |
| Object | Iglesia católica |
—
|
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: Iglesia católica | Statement: [Ley sobre Libertad de Cultos, grupoAfectado, Iglesia católica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grupoAfectado Context triple: [Ley sobre Libertad de Cultos, grupoAfectado, Iglesia católica]
-
A.
affectedPeople
Indicates the people who are impacted or influenced by a particular event, action, or condition.
-
B.
familyAffectedBy
Indicates that one or more members of a person’s family experience or are impacted by a specified condition, event, or circumstance.
-
C.
affectedPerson
Indicates that a particular person is impacted or influenced by an event, action, or condition.
-
D.
affectedEthnicGroup
chosen
Indicates that a particular ethnic group is impacted or influenced by an event, condition, policy, or action.
-
E.
standAffected
Indicates that an entity is in a state or position of being impacted or influenced by another entity or event.
- 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_69f224a5d2b481908a6853cd0138e2d7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a9b821c8190bf6d788b02a58baa |
completed | May 2, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:30 p.m.