Triple
T4287874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donatello |
E97313
|
entity |
| Predicate | workedWithMaterial |
P21333
|
FINISHED |
| Object | bronze |
—
|
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: bronze | Statement: [Donatello, workedWithMaterial, bronze]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedWithMaterial Context triple: [Donatello, workedWithMaterial, bronze]
-
A.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
B.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
-
C.
workUsedAs
Indicates that one work is employed or utilized in the creation, performance, or presentation of another work.
-
D.
worksAgainst
Indicates that one entity actively opposes, counteracts, or undermines the goals, effects, or interests of another entity.
-
E.
madeWith
chosen
Indicates that one entity is created, produced, or constructed using another entity as a material, ingredient, or component.
- 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_69b3454595848190a0e6bbb6a2bea040 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3505ef9fc81909c73e64bf77052ce |
completed | March 12, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69b347fc4c0c8190a7fcd814e27308a5 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:08 p.m.