Triple
T9857373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Expressway S17 |
E239620
|
entity |
| Predicate | continuesTowards |
P77537
|
FINISHED |
| Object | Ukrainian border |
—
|
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: Ukrainian border | Statement: [Expressway S17, continuesTowards, Ukrainian border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: continuesTowards Context triple: [Expressway S17, continuesTowards, Ukrainian border]
-
A.
continuesToward
chosen
Indicates that an entity maintains its movement or progression in the direction of a specified target or destination.
-
B.
continuesOn
Indicates that an action, process, or state persists or carries forward beyond a given point, without interruption or termination.
-
C.
continuedBy
Indicates that one entity carries on, extends, or resumes the activity, process, or sequence initiated by another entity.
-
D.
continuityFrom
Indicates that one entity continues, extends, or proceeds directly from another in a seamless or unbroken manner.
-
E.
losesTo
Indicates that one entity is defeated by or comes out worse than another in a competitive or comparative context.
- 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_69ca84e6493081909cf58c8d42ea856b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb39864188190a2d8c0ee911f00c2 |
completed | April 2, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:35 p.m.