Triple
T25973624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | York Museum Gardens |
E645874
|
entity |
| Predicate | heritageContains |
P163831
|
FINISHED |
| Object | Roman ruins |
—
|
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: Roman ruins | Statement: [York Museum Gardens, heritageContains, Roman ruins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageContains Context triple: [York Museum Gardens, heritageContains, Roman ruins]
-
A.
hasHeritageElements
chosen
Indicates that something contains or includes elements that are part of a cultural, historical, or natural heritage.
-
B.
hasHeritage
Indicates that an entity possesses or is associated with a particular cultural, ethnic, or ancestral background.
-
C.
hasHeritageValueFor
Indicates that something possesses cultural, historical, or heritage significance for a particular entity or community.
-
D.
heritageFor
Indicates that something serves as a source, basis, or contributing legacy for another entity’s heritage or tradition.
-
E.
hasHeritageFeature
Indicates that an entity possesses or includes a feature recognized as part of cultural, historical, or natural heritage.
- 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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f661b58ac48190907b6c6e9ccc2c59 |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f660eea4648190b0d5e24293607813 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 22, 2026, 8:51 a.m.