Triple
T13910683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matrona (young girl, according to tradition) |
E334482
|
entity |
| Predicate | iconTypeDiscovered |
P25799
|
FINISHED |
| Object | Marian icon |
—
|
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 icon | Statement: [Matrona (young girl, according to tradition), iconTypeDiscovered, Marian icon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iconTypeDiscovered Context triple: [Matrona (young girl, according to tradition), iconTypeDiscovered, Marian icon]
-
A.
iconOf
Indicates that one entity serves as a symbolic or representative image or emblem of another entity.
-
B.
discoveredFeature
Indicates that an entity has identified or uncovered a previously unknown or unrecognized feature of another entity or object.
-
C.
discoveredAs
chosen
Indicates that one entity was first identified, found, or recognized in the role or form specified by another entity.
-
D.
discoveredWith
Indicates that one entity was found, detected, or identified using another entity as the means, tool, method, or accompanying context of discovery.
-
E.
madeDiscoveryOn
Indicates that an entity discovered or identified something on a specific date or at a specific point in time.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2723461881908376b5509ee0d530 |
completed | April 14, 2026, 11:38 a.m. |
| PD | Predicate disambiguation | batch_69de059e4ba881908554f72e889719fa |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:16 p.m.