Triple
T12441241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | religious shrine of the Virgin of Andacollo |
E297274
|
entity |
| Predicate | numberOfPilgrims |
P45240
|
FINISHED |
| Object | thousands per year |
—
|
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: thousands per year | Statement: [religious shrine of the Virgin of Andacollo, numberOfPilgrims, thousands per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfPilgrims Context triple: [religious shrine of the Virgin of Andacollo, numberOfPilgrims, thousands per year]
-
A.
hasPilgrims
Indicates that an entity is associated with or contains pilgrims, typically as visitors, members, or participants in a pilgrimage.
-
B.
primaryPilgrims
Indicates that the referenced entities are the main or principal participants undertaking a pilgrimage in relation to something or someone.
-
C.
pilgrimsFrom
Indicates that one or more pilgrims originate from, or are associated with coming from, a particular place.
-
D.
pilgrimsPerYearApprox
chosen
Indicates an approximate number of pilgrims who travel to a place within a year.
-
E.
pilgrimCapacity
Indicates the maximum number of pilgrims that an entity (such as a facility, vehicle, or location) is designed or allowed to accommodate.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.