Triple
T9154765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Misión San Francisco Javier de Viggé-Biaundó |
E219680
|
entity |
| Predicate | languageOfEvangelization |
P54680
|
FINISHED |
| Object | Spanish |
—
|
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: Spanish | Statement: [Misión San Francisco Javier de Viggé-Biaundó, languageOfEvangelization, Spanish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfEvangelization Context triple: [Misión San Francisco Javier de Viggé-Biaundó, languageOfEvangelization, Spanish]
-
A.
languageOfGospelTraditionally
Indicates the language in which a particular Gospel is traditionally believed or held to have been written or transmitted.
-
B.
languageOfWorship
Indicates the language in which religious worship, rituals, or liturgical practices are conducted.
-
C.
liturgicalLanguageVersion
Indicates that one entity is a specific version or form of another entity expressed in a particular liturgical language.
-
D.
languageOfTransmission
chosen
Indicates the language used to convey or transmit the content or information in a given communication or resource.
-
E.
languageOfReligiousLife
Indicates the language primarily used in the religious practices, rituals, or spiritual life associated with an 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_69ca83e25418819093c6503deeaf30de |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca96f87ac8190b2fc6d2b2834c1b6 |
completed | April 1, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69cc6605c6808190a30d92da006206ac |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:20 p.m.