Triple
T9912135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ecce Ancilla Domini! |
E185168
|
entity |
| Predicate | collection |
P426
|
FINISHED |
| Object | Tate |
E86288
|
NE 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: Tate | Statement: [Ecce Ancilla Domini!, collection, Tate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tate Context triple: [Ecce Ancilla Domini!, collection, Tate]
-
A.
Tate
Tate is a given name most commonly associated with the American actor and director Tate Donovan.
-
B.
Tate
chosen
Tate is a UK-based art institution and network of galleries that houses and promotes the national collection of British art and significant international modern and contemporary works.
-
C.
Bridgeman
Bridgeman is an English surname historically associated with British nobility and aristocratic families.
-
D.
William Tate
William Tate was a British businessman known for his partnership with sugar magnate Sir Henry Tate in the 19th-century sugar industry.
-
E.
William Tate
William Tate was a French military officer who led the failed 1797 French invasion of Wales, often regarded as the last attempted invasion of Britain.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8296165881908ca4750701af1f29 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb5391b8081908094b88cdde4b55a |
completed | April 2, 2026, 12:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228ae315c8190bedb2cbab0982118 |
completed | April 5, 2026, 9:17 a.m. |
Created at: March 30, 2026, 8:41 p.m.