Triple
T35413555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schierke station |
E1023575
|
entity |
| Predicate | keyAccessPointFor |
P96810
|
FINISHED |
| Object | Brocken peak |
—
|
NE NERFINISHED |
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: Brocken peak | Statement: [Schierke station, keyAccessPointFor, Brocken peak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyAccessPointFor Context triple: [Schierke station, keyAccessPointFor, Brocken peak]
-
A.
keyPosition
Indicates the specific location or placement of a key within a defined space or system.
-
B.
keyTarget
Indicates that one entity serves as the primary focus, objective, or intended recipient of another entity’s action, function, or influence.
-
C.
keyResolution
Indicates the specific tonal center and mode (key) in which a piece of music or musical passage ultimately settles or resolves.
-
D.
keyAccord
Indicates that one entity’s key or signature matches, agrees with, or is compatible with that of another entity.
-
E.
keyAssociation
chosen
Indicates an associative relationship where one entity serves as a key used to identify, access, or link to another entity or set of entities.
- 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_69f76df54bac8190bd0d3b0eb35cda5f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7956a3444819093748feaf7c4a7aa |
completed | May 3, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.