Triple
T3220331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freetown Christiania |
E67496
|
entity |
| Predicate | formerUseOfArea |
P2417
|
FINISHED |
| Object | Danish military barracks |
—
|
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: Danish military barracks | Statement: [Freetown Christiania, formerUseOfArea, Danish military barracks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerUseOfArea Context triple: [Freetown Christiania, formerUseOfArea, Danish military barracks]
-
A.
formerLandUse
Indicates the type of land use that characterized a location prior to its current or present use.
-
B.
historicallyUsedFor
chosen
Indicates that something served a particular function or purpose at some point in the past, even if it may no longer be used that way now.
-
C.
locatedInFormerAdministrativeTerritory
Indicates that an entity is situated within the boundaries of an administrative territory that no longer exists or has been reorganized.
-
D.
historicallyPartOf
Indicates that one entity was formerly a component, region, or subdivision of another entity during a past historical period, but is not necessarily part of it in the present.
-
E.
formerNameOfDistrict
Indicates that one district previously had a different official name, which is the value linked by this predicate.
- 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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adae16f20081909d7f3bac016f961d |
completed | March 8, 2026, 5:12 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0bb6c48190a0659c67d40ee37c |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:08 p.m.