Triple
T25202488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Unit |
E631157
|
entity |
| Predicate | isLargestSectionOf |
P61335
|
FINISHED |
| Object | Theodore Roosevelt National Park |
—
|
NE NERFINISHED |
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: Theodore Roosevelt National Park | Statement: [South Unit, isLargestSectionOf, Theodore Roosevelt National Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLargestSectionOf Context triple: [South Unit, isLargestSectionOf, Theodore Roosevelt National Park]
-
A.
isLargestOf
Indicates that one entity has the greatest size, extent, or magnitude among a specified set of entities.
-
B.
hasLargestAreaOf
Indicates that the subject entity possesses the greatest area (size of surface or region) compared to the other entities in the specified set or context.
-
C.
largestPartIn
chosen
Indicates that one entity is the largest component or segment contained within another entity.
-
D.
areLargestGroupIn
Indicates that one group is the biggest or most numerous among all groups within a specified context or set.
-
E.
isMultiSectional
Indicates that something is composed of or divided into multiple distinct sections or parts.
- 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_69e75a8b86c4819089eda22c843b739f |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f474b904f48190be6513788f89c6a9 |
completed | May 1, 2026, 9:39 a.m. |
| PD | Predicate disambiguation | batch_69f45cfb53f4819099bba48c5057e787 |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 12:51 p.m.