Triple
T8852769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East Entrance |
E210676
|
entity |
| Predicate | positionOnPark |
P3250
|
FINISHED |
| Object | eastern side of Zion National Park |
—
|
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: eastern side of Zion National Park | Statement: [East Entrance, positionOnPark, eastern side of Zion National Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionOnPark Context triple: [East Entrance, positionOnPark, eastern side of Zion National Park]
-
A.
startingPark
Indicates that an entity begins or initiates its activity, route, or presence from a specified park.
-
B.
parkServed
Indicates that a particular park is provided with services or coverage by a specified entity (such as a transit line, facility, or administrative body).
-
C.
isWithinPark
Indicates that one entity is located inside the boundaries of a park that contains it.
-
D.
positionOn
chosen
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
E.
positionOnRace
Indicates the relative ranking or placement an entity holds within the context of a race or competitive event.
- 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_69ca838a424c8190b1ecac115c2927e7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60c55e348190957b3bbb7397e380 |
completed | April 1, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69cc5c25b874819084c9ba391703e066 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:49 p.m.