Triple
T9691824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Via Krupp |
E234553
|
entity |
| Predicate | followsCliff |
P1865
|
FINISHED |
| Object | Capri southern coast cliffs |
—
|
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: Capri southern coast cliffs | Statement: [Via Krupp, followsCliff, Capri southern coast cliffs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsCliff Context triple: [Via Krupp, followsCliff, Capri southern coast cliffs]
-
A.
hasCliff
Indicates that something possesses or features a steep, high rock face or abrupt vertical drop as part of its structure or environment.
-
B.
followsCoast
chosen
Indicates that one entity’s path or boundary runs alongside and generally conforms to the shape of a coastline.
-
C.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
D.
climbsTo
Indicates that one entity moves upward, typically with effort or by climbing, until it reaches another entity or a higher position.
-
E.
hasCliffsOn
Indicates that one entity possesses or features cliffs located along or on the surface of 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_69ca84ca73208190957a900c8543bdcc |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9d05d70c8190b1ddcd24b50b4f50 |
completed | April 1, 2026, 10:32 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b840f081909f66bf0b66d17d9b |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:17 p.m.