Triple
T25554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Livadia Palace |
E510
|
entity |
| Predicate | hasExhibition |
P1513
|
FINISHED |
| Object | Romanov family memorabilia |
—
|
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: Romanov family memorabilia | Statement: [Livadia Palace, hasExhibition, Romanov family memorabilia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExhibition Context triple: [Livadia Palace, hasExhibition, Romanov family memorabilia]
-
A.
hasReception
Indicates that an entity hosts, includes, or is associated with a reception event (such as a formal gathering or welcoming function).
-
B.
participatedInEvent
Indicates that an entity took part in or was actively involved in a specific event.
-
C.
presentedBy
Indicates that something (such as an event, performance, or work) is formally organized, hosted, or introduced by a particular person or entity.
-
D.
meetsAs
Indicates that two entities encounter or come together at the same place and time, typically in a planned or recognized interaction.
-
E.
hasExample
Indicates that one entity serves as an instance, illustration, or concrete example of another entity.
- F. None of above. chosen
Provenance (4 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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a246d794448190bb2844fcd0538eaa |
completed | Feb. 28, 2026, 1:37 a.m. |
| PD | Predicate disambiguation | batch_69a24657635881908f3415bc1bdfa1b5 |
completed | Feb. 28, 2026, 1:35 a.m. |
| PDg | Predicate description generation | batch_69a246d6aca88190a86b7c41d497bacd |
completed | Feb. 28, 2026, 1:37 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.