Triple
T38575788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alpine Line |
E929396
|
entity |
| Predicate | someSitesUsedAs |
P116266
|
FINISHED |
| Object | museums |
—
|
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: museums | Statement: [Alpine Line, someSitesUsedAs, museums]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: someSitesUsedAs Context triple: [Alpine Line, someSitesUsedAs, museums]
-
A.
usedOnWebsites
Indicates that something is employed or implemented as part of the content, functionality, or infrastructure of websites.
-
B.
originalSiteUse
Indicates the historical or initial functional use or purpose assigned to a particular site before any subsequent changes or developments.
-
C.
hasSiteUse
Indicates that a site is used or designated for a particular function, activity, or purpose.
-
D.
reusesSiteOf
Indicates that one entity occupies or uses the same site or location that was previously used by another entity.
-
E.
isSometimesUsedFor
chosen
Indicates that something serves a particular purpose or function on some occasions, but not consistently or exclusively.
- 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_69f76ebd2248819083978362d81fa35e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.