Triple
T28039334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | West Seattle Bridge |
E708493
|
entity |
| Predicate | hasBarriers |
P87527
|
FINISHED |
| Object | concrete safety 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: concrete safety barriers | Statement: [West Seattle Bridge, hasBarriers, concrete safety barriers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBarriers Context triple: [West Seattle Bridge, hasBarriers, concrete safety barriers]
-
A.
isBarrierTo
Indicates that one entity obstructs, prevents, or significantly hinders another entity from occurring, progressing, or being accessed.
-
B.
hasObstructions
Indicates that one entity is blocking, hindering, or limiting another entity’s movement, function, or access.
-
C.
hasGuardBars
chosen
Indicates that one entity is equipped with or protected by guard bars installed on or around it.
-
D.
typicalBarrierType
Indicates the usual or characteristic type of barrier associated with or used in a given context or situation.
-
E.
facedBarrier
Indicates that an entity encountered an obstacle, hindrance, or restriction that impeded its progress or actions.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 27, 2026, 8:23 p.m.