Triple
T1398160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Forge Lake Cruises |
E30716
|
entity |
| Predicate | tourDurationType |
P22194
|
FINISHED |
| Object | short excursions |
—
|
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: short excursions | Statement: [Old Forge Lake Cruises, tourDurationType, short excursions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourDurationType Context triple: [Old Forge Lake Cruises, tourDurationType, short excursions]
-
A.
rideDuration
Indicates the length of time that a ride or trip lasts from start to finish.
-
B.
rideType
Indicates the specific category or mode of transportation involved in a ride (e.g., standard, shared, premium).
-
C.
travelTimeCategory
chosen
Indicates the qualitative classification of how long a given travel or trip duration is (e.g., short, medium, long).
-
D.
missionDurationType
Indicates the classification of a mission’s length or time span (e.g., short-term, long-term, extended).
-
E.
fareType
Indicates the category or class of fare (such as standard, discounted, or promotional) that applies to a given trip, ticket, or pricing instance.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c382b6588190833c39ac84fb6139 |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.