Triple
T11525176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Tyndall |
E273274
|
entity |
| Predicate | usualApproach |
P77723
|
FINISHED |
| Object | via Shepherd Pass |
—
|
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: via Shepherd Pass | Statement: [Mount Tyndall, usualApproach, via Shepherd Pass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usualApproach Context triple: [Mount Tyndall, usualApproach, via Shepherd Pass]
-
A.
standardApproach
chosen
Indicates that an entity uses or follows a commonly accepted, conventional, or typical method for addressing a task or problem.
-
B.
controlledApproachTo
Indicates a deliberate, regulated, or carefully managed way of proceeding toward or dealing with another entity.
-
C.
notTypically
Indicates that the referenced situation, behavior, or relationship does not usually or normally occur under standard or expected conditions.
-
D.
typicalPractice
Indicates that an action, behavior, or method is commonly or customarily done in a given context or by a given group.
-
E.
ordinary
Indicates that something or someone is typical, usual, or not special or exceptional in the relevant context.
- 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_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d87fd379648190b342e0c4b4f685b7 |
completed | April 10, 2026, 4:42 a.m. |
| PD | Predicate disambiguation | batch_69d80879fdb48190be6dacc8aa63c809 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.