Triple

T27680197
Position Surface form Disambiguated ID Type / Status
Subject Tower–Roosevelt area E697886 entity
Predicate hasLandmark P105 FINISHED
Object Petrified Tree area
The Petrified Tree area is a notable site in Yellowstone National Park where visitors can view a large, well-preserved fossilized tree trunk and learn about the park’s ancient volcanic and forest history.
 E1783306 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: Petrified Tree area | Statement: [Tower–Roosevelt area, hasLandmark, Petrified Tree area]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Petrified Tree area
Triple: [Tower–Roosevelt area, hasLandmark, Petrified Tree area]
Generated description
The Petrified Tree area is a notable site in Yellowstone National Park where visitors can view a large, well-preserved fossilized tree trunk and learn about the park’s ancient volcanic and forest history.

Provenance (5 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_69ef590d458c81909583290c3cd0478b completed April 27, 2026, 12:39 p.m.
NER Named-entity recognition batch_69f635383864819095574ddc05b9a51f completed May 2, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12daadb7e48190a6f75b1f7ea098ec completed May 24, 2026, 11:02 a.m.
NEDg Description generation batch_6a12db5d2878819094252a665596a86e completed May 24, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_6a12dbe4c9e4819084be4a4f5e3b58a6 completed May 24, 2026, 11:07 a.m.
Created at: April 27, 2026, 2:46 p.m.