Triple
T26085260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Library of Turin |
E657959
|
entity |
| Predicate | holdsItem |
P150044
|
FINISHED |
| Object | Leonardo da Vinci self-portrait drawing |
—
|
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: Leonardo da Vinci self-portrait drawing | Statement: [Royal Library of Turin, holdsItem, Leonardo da Vinci self-portrait drawing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsItem Context triple: [Royal Library of Turin, holdsItem, Leonardo da Vinci self-portrait drawing]
-
A.
materialHeldAt
chosen
Indicates that a material is physically stored or kept at a specific location or facility.
-
B.
canBeHeldWith
Indicates that two entities are compatible or suitable to be held or used together at the same time.
-
C.
possessedItem
Indicates that one entity owns, holds, or has control over another entity as a possession.
-
D.
typicallyHolds
Indicates that a certain relationship or condition generally holds true in typical or normal situations, though not necessarily in all cases.
-
E.
oftenEquippedWith
Indicates that one type of entity is frequently or typically outfitted, furnished, or supplied with another entity.
- 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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f606ff5eb88190bd0390fd9cf1e38d |
completed | May 2, 2026, 2:15 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 7:42 p.m.