Triple
T36173193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cedar Tree Tower |
E1046501
|
entity |
| Predicate | associatedWithParkFeature |
P54593
|
FINISHED |
| Object | Mesa Top Loop archaeological overlooks |
E323485
|
NE 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: Mesa Top Loop archaeological overlooks | Statement: [Cedar Tree Tower, associatedWithParkFeature, Mesa Top Loop archaeological overlooks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithParkFeature Context triple: [Cedar Tree Tower, associatedWithParkFeature, Mesa Top Loop archaeological overlooks]
-
A.
associatedWithPark
Indicates a relationship in which an entity is connected or linked in some relevant way to a particular park.
-
B.
hasParkFeature
chosen
Indicates that a park includes, contains, or is associated with a specific feature or amenity.
-
C.
parkFeature
Indicates that a particular feature, amenity, or element is part of, located within, or characteristic of a park.
-
D.
hasNearbyParkFeature
Indicates that one place or object is located close to a park-related feature, such as a park, playground, or green space.
-
E.
hasParkAccess
Indicates that an entity is permitted to enter, use, or otherwise access a specified park or park area.
- F. None of above.
Provenance (4 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_69f76e3c1b10819081fc7a807a71cf84 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a390d5cafc481909d61c55d1aa1d891 |
completed | June 22, 2026, 10:24 a.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:08 p.m.