Triple
T9283647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beach Trail |
E223130
|
entity |
| Predicate | trailDirection |
P76664
|
FINISHED |
| Object | downhill from bluffs to beach |
—
|
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: downhill from bluffs to beach | Statement: [Beach Trail, trailDirection, downhill from bluffs to beach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailDirection Context triple: [Beach Trail, trailDirection, downhill from bluffs to beach]
-
A.
transportDirection
Indicates the directional flow or route along which something is transported from an origin toward a destination.
-
B.
routeDirectionB
chosen
Indicates that one entity represents the direction or orientation of a route or path relative to another entity.
-
C.
routeDirectionA
Indicates the primary or first directional orientation or heading associated with a specific route.
-
D.
travelsDirection
Indicates that an entity moves or is transported in a specified directional heading or orientation.
-
E.
hasStreetDirection
Indicates that a street or road segment is associated with a specific directional orientation (e.g., northbound, east-west).
- 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_69ca842123588190b3f2e1a69037d141 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd081e72988190917f425e64631837 |
completed | April 1, 2026, 11:57 a.m. |
| PD | Predicate disambiguation | batch_69cc7a576ec88190bbb787eb82e2e539 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:34 p.m.