Triple
T28815431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Patrick’s Oratory |
E727628
|
entity |
| Predicate | pilgrimageMountain |
P11789
|
FINISHED |
| Object | Croagh Patrick |
—
|
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: Croagh Patrick | Statement: [St Patrick’s Oratory, pilgrimageMountain, Croagh Patrick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pilgrimageMountain Context triple: [St Patrick’s Oratory, pilgrimageMountain, Croagh Patrick]
-
A.
hasPilgrimagePeak
chosen
Indicates that a place or route is associated with a specific peak that serves as a destination or focal point for religious or spiritual pilgrimage.
-
B.
holyMountain
Indicates that a mountain is regarded as sacred or religiously significant within a particular belief system or tradition.
-
C.
pilgrimageAssociatedWith
Indicates a relationship where a pilgrimage is connected or related to a particular entity, such as a place, person, event, or religious tradition.
-
D.
pilgrimageSince
Indicates that an entity has been engaged in or committed to a pilgrimage starting from a specified point in time.
-
E.
pilgrimageRouteTo
Indicates a route or path that is traditionally used or designated for making a religious or spiritual pilgrimage to a particular destination.
- 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658f37af88190a1dda8efcd28c34b |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:32 a.m.