Triple
T1293301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabella Stewart Gardner Museum |
E27595
|
entity |
| Predicate | estimatedValueOfStolenWorks |
P25888
|
FINISHED |
| Object | 500000000 USD |
—
|
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: 500000000 USD | Statement: [Isabella Stewart Gardner Museum, estimatedValueOfStolenWorks, 500000000 USD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedValueOfStolenWorks Context triple: [Isabella Stewart Gardner Museum, estimatedValueOfStolenWorks, 500000000 USD]
-
A.
donatedArtwork
Indicates that one entity has given a piece of artwork as a donation to another entity or institution.
-
B.
economicDamageApprox
chosen
Indicates that one entity has caused or is associated with an estimated or approximate amount of economic damage to another entity or system.
-
C.
estimatedNumberOfPaintings
Indicates the approximate count of paintings associated with an entity, rather than an exact, verified number.
-
D.
soldRecordsEstimate
Indicates an approximate number of sales transactions or records associated with an entity.
-
E.
currencyDamageEstimateNetherlands
Indicates an assessment of monetary damage or loss specifically calculated for the Netherlands.
- 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_69a496d4ec448190ad653b2590c46711 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c3bb3a9c81909db2ad91defd87b6 |
completed | March 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69a4bee64d908190b6a9bb479959d523 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:51 p.m.