Triple
T26496550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Our Lady of Le Puy |
E669296
|
entity |
| Predicate | hasAssociatedRelicOrImage |
P23131
|
FINISHED |
| Object | statue of the Virgin and Child |
—
|
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: statue of the Virgin and Child | Statement: [Our Lady of Le Puy, hasAssociatedRelicOrImage, statue of the Virgin and Child]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAssociatedRelicOrImage Context triple: [Our Lady of Le Puy, hasAssociatedRelicOrImage, statue of the Virgin and Child]
-
A.
hasRelicsStatus
Indicates that an entity holds a particular status or condition specifically related to relics.
-
B.
containsRelic
Indicates that one entity holds, includes, or has within it a relic.
-
C.
hasRelicType
Indicates that an entity is associated with, classified by, or possesses a specific type or category of relic.
-
D.
hasHeirloom
Indicates that one entity possesses or is associated with an heirloom originating from another entity.
-
E.
hasIconicArtifact
chosen
Indicates that an entity possesses or is associated with a distinctive, emblematic artifact that represents its identity, history, or significance.
- 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_69eeb319007081909642b414b114b35a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f661b58ac48190907b6c6e9ccc2c59 |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f660eea4648190b0d5e24293607813 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 27, 2026, 1:09 a.m.