Triple
T2676164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dumbarton Oaks |
E56463
|
entity |
| Predicate | hasByzantineCollectionItems |
P426
|
FINISHED |
| Object | mosaics |
—
|
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: mosaics | Statement: [Dumbarton Oaks, hasByzantineCollectionItems, mosaics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasByzantineCollectionItems Context triple: [Dumbarton Oaks, hasByzantineCollectionItems, mosaics]
-
A.
hasMosaicsBy
Indicates that something contains or features mosaics that were created by a specified agent or creator.
-
B.
hasCollection
chosen
Indicates that an entity possesses, maintains, or is associated with a set or group of related items treated as a collection.
-
C.
hasCollectionItemBy
Indicates that an entity possesses or includes a specific item as part of its collection, identified or referenced by some key or identifier.
-
D.
hasSpecialCollections
Indicates that an entity possesses or maintains distinct, curated collections that are set apart from its general holdings.
-
E.
hasCollectionFrom
Indicates that an entity possesses or maintains a collection that originates from, or is sourced from, another specified 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_69ab4a4b13fc81909dfdb3f23da46832 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abda2f7bf88190a1e3103dd014d871 |
completed | March 7, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69abd81ab9d08190b72b6104c6dbc769 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:54 p.m.