Triple
T27896694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Havana City Hall |
E705511
|
entity |
| Predicate | heritageStatusOfHostBuilding |
P175984
|
FINISHED |
| Object | museum building |
—
|
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: museum building | Statement: [Havana City Hall, heritageStatusOfHostBuilding, museum building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageStatusOfHostBuilding Context triple: [Havana City Hall, heritageStatusOfHostBuilding, museum building]
-
A.
heritageStatus
Indicates that an entity holds a particular cultural, historical, or natural heritage designation or protection status.
-
B.
cityHeritageStatus
Indicates that a city holds a specific heritage designation or status, such as being recognized for its historical, cultural, or architectural significance.
-
C.
heritageStatusOfCathedral
Indicates the heritage designation or protection status assigned to a cathedral.
-
D.
heritageProtectionType
Indicates the specific kind or category of legal or formal protection applied to a heritage asset or site.
-
E.
residenceHistoric
Indicates that a residence has historical significance or is formally recognized as a historic dwelling.
- 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_69ef96b490ac8190a412d04c5d009f3e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6db3606808190a80c6e9f5da5b33e |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
| PDg | Predicate description generation | batch_69f6db1bc348819097c844f76e2fa4fe |
completed | May 3, 2026, 5:20 a.m. |
Created at: April 27, 2026, 6:39 p.m.