Triple
T4354748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ave Maria Grotto |
E98118
|
entity |
| Predicate | hasReligiousFocus |
P24743
|
FINISHED |
| Object | Marian devotion |
—
|
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: Marian devotion | Statement: [Ave Maria Grotto, hasReligiousFocus, Marian devotion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReligiousFocus Context triple: [Ave Maria Grotto, hasReligiousFocus, Marian devotion]
-
A.
hasReligiousTheme
chosen
Indicates that something (such as a work, event, or object) centrally involves or expresses religious ideas, symbols, practices, or narratives.
-
B.
hasReligiousCharacter
Indicates that an entity possesses a religious nature, function, or affiliation, or is characterized by religious aspects or significance.
-
C.
hasReligiousOrigin
Indicates that something originates from, is derived from, or is fundamentally based on a religious tradition, belief system, or practice.
-
D.
hasAssociatedReligion
Indicates that an entity is connected with or linked to a particular religion.
-
E.
bearerReligion
Indicates that a bearer (such as a person or entity) adheres to, practices, or is associated with a particular religion.
- 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_69b3454965f881908c41190bb22f0e4b |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351c3aa1c8190aacebb8e80e5f2f8 |
completed | March 12, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69b34f51ed7c8190b7bf5f44b56b730d |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:16 p.m.