Triple
T35184767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Our Lady of the Roses |
E1015954
|
entity |
| Predicate | messagesClaimSource |
P116977
|
FINISHED |
| Object | Virgin Mary |
—
|
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: Virgin Mary | Statement: [Our Lady of the Roses, messagesClaimSource, Virgin Mary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: messagesClaimSource Context triple: [Our Lady of the Roses, messagesClaimSource, Virgin Mary]
-
A.
claimsSource
chosen
Indicates that one entity is identified as the origin or provider of a claim made by another entity.
-
B.
mainClaim
Indicates that one statement is presented as the central or primary assertion being made about a topic.
-
C.
recordClaim
Indicates that an entity formally documents or logs a claim made by another entity or about a particular matter.
-
D.
facedClaimsFrom
Indicates that one entity has been the target of accusations, allegations, or formal complaints made by another entity.
-
E.
labelClaim
Indicates that an entity asserts or assigns a specific label or classification to another entity or statement.
- 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_69f76ddd815c8190b822eea06630f9fb |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78dc196708190a1a1cf7b9068e1cd |
completed | May 3, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.