Triple
T28636818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dresden Green Diamond |
E724810
|
entity |
| Predicate | historicallyHousedAt |
P35508
|
FINISHED |
| Object | Dresden Castle |
—
|
NE NERFINISHED |
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: Dresden Castle | Statement: [Dresden Green Diamond, historicallyHousedAt, Dresden Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyHousedAt Context triple: [Dresden Green Diamond, historicallyHousedAt, Dresden Castle]
-
A.
historicallyHoused
chosen
Indicates that one entity served as a location or container for another entity at some time in the past.
-
B.
historicalLocationOf
Indicates that a place served as a significant site or setting for an entity during a particular historical period or event.
-
C.
historicallyPlacedIn
Indicates that an entity was located or situated in a particular place during a specific historical period or context.
-
D.
wasHeadquartersDuring
Indicates that a particular location served as the headquarters of an entity during a specified time period.
-
E.
historicallyLocatedNear
Indicates that, in a historical context, one entity was geographically situated close to another 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_69f01d8328c48190bc0e5f9b9b848582 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
Created at: April 28, 2026, 4:41 a.m.