Triple
T19800869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunhinda Falls |
E475669
|
entity |
| Predicate | hasLocalVendors |
P50801
|
FINISHED |
| Object | food stalls along trail |
—
|
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: food stalls along trail | Statement: [Dunhinda Falls, hasLocalVendors, food stalls along trail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalVendors Context triple: [Dunhinda Falls, hasLocalVendors, food stalls along trail]
-
A.
eligibleVendors
Indicates that certain vendors meet the required criteria or conditions to be considered eligible for a specified purpose or process.
-
B.
hasLocalSupport
Indicates that an entity receives backing, endorsement, or assistance from people or organizations within its immediate geographic or community area.
-
C.
hasFoodVendors
chosen
Indicates that one entity provides or hosts food vendors that operate at or within another entity.
-
D.
hasApproximateVendorCount
Indicates that an entity is associated with an estimated or non-exact number of vendors.
-
E.
hasLocalBoards
Indicates that an entity is associated with one or more governing or administrative boards operating at a local or regional level.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653cc995c81908e4ca85b0639d541 |
completed | April 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e5305858108190bbbfdb9ba3ab9f80 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:49 p.m.