Triple
T13821835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hala Gąsienicowa |
E332155
|
entity |
| Predicate | trailColorAccess |
P14031
|
FINISHED |
| Object | blue trail from Kuźnice |
—
|
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: blue trail from Kuźnice | Statement: [Hala Gąsienicowa, trailColorAccess, blue trail from Kuźnice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailColorAccess Context triple: [Hala Gąsienicowa, trailColorAccess, blue trail from Kuźnice]
-
A.
trackColor
Indicates the color associated with a given track in a context such as audio, video, or data sequencing.
-
B.
trailAccess
Indicates that one entity provides permission or a route for another entity to enter, use, or traverse a specific trail or pathway.
-
C.
colorOfTrailMarkings
chosen
Indicates the relationship specifying what color the trail’s markings are.
-
D.
trailAssociation
Indicates an associative relationship between entities where one is contextually or functionally linked to a trail (such as being located on, connected to, or part of that trail).
-
E.
trailName
Indicates the name assigned to a specific trail or path in the relationship.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0284428081908043c55caeefb833 |
completed | April 14, 2026, 9:01 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:12 p.m.