Triple
T15880114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mancunian Way |
E385052
|
entity |
| Predicate | hasCrashBarriers |
P81815
|
FINISHED |
| Object | central reservation barriers |
—
|
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: central reservation barriers | Statement: [Mancunian Way, hasCrashBarriers, central reservation barriers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCrashBarriers Context triple: [Mancunian Way, hasCrashBarriers, central reservation barriers]
-
A.
hasGuardBars
Indicates that one entity is equipped with or protected by guard bars installed on or around it.
-
B.
isBarrierTo
Indicates that one entity obstructs, prevents, or significantly hinders another entity from occurring, progressing, or being accessed.
-
C.
hasBars
chosen
Indicates that one entity possesses, contains, or is equipped with bars as a defining feature or component.
-
D.
hasCrack
Indicates that one entity possesses or exhibits a crack, fracture, or split in its structure or surface.
-
E.
hasSkyBar
Indicates that an establishment features a bar located on its rooftop or at a high elevation with views of the surrounding area.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e174de2cd48190ab18e48c9f051a2a |
completed | April 16, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69e142c3e18c8190bb7b023f4a0eaebb |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:51 a.m.