Triple
T20871540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarajevo Trolleybus |
E513903
|
entity |
| Predicate | hasWireSystem |
P116256
|
FINISHED |
| Object | dual overhead trolley wires |
—
|
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: dual overhead trolley wires | Statement: [Sarajevo Trolleybus, hasWireSystem, dual overhead trolley wires]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWireSystem Context triple: [Sarajevo Trolleybus, hasWireSystem, dual overhead trolley wires]
-
A.
isWired
Indicates that one entity is physically connected to another via electrical or data wiring.
-
B.
hasWirePlaneType
chosen
Indicates that an entity is associated with or characterized by a specific type of wire plane.
-
C.
isTypicallyWiredUsing
Indicates that one thing is commonly connected or implemented using a particular type of wiring or cabling.
-
D.
hasWireAngle
Indicates that one entity has a wire oriented or positioned at a specific angle relative to another reference or component.
-
E.
hasNumberOfWirePlanes
Indicates that an entity is associated with a specified count of wire planes it possesses or uses.
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c4649cf88190b3ad946576aa46aa |
completed | April 21, 2026, 12:27 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a593f481908beb457c29f1ce73 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:45 p.m.