Triple

T27330100
Position Surface form Disambiguated ID Type / Status
Subject Kasigluk, Alaska E689773 entity
Predicate locatedOn P40 FINISHED
Object Johnson River
Johnson River is a river in southwestern Alaska that flows through the Yukon–Kuskokwim Delta region and passes by the village of Kasigluk.
 E2293996 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: Johnson River | Statement: [Kasigluk, Alaska, locatedOn, Johnson River]
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: Johnson River
Triple: [Kasigluk, Alaska, locatedOn, Johnson River]
Generated description
Johnson River is a river in southwestern Alaska that flows through the Yukon–Kuskokwim Delta region and passes by the village of Kasigluk.

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_69ef355d4cb08190ab032c0a2e7d3753 completed April 27, 2026, 10:07 a.m.
NER Named-entity recognition batch_69f62aca6ba48190bf2be364412d4944 completed May 2, 2026, 4:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a7b5f893c948190964d6c7638b02a02 completed Aug. 11, 2026, 5:44 p.m.
NEDg Description generation batch_6a7b5ff24f508190af10fd1962575dbf completed Aug. 11, 2026, 5:46 p.m.
NED2 Entity disambiguation (via description) batch_6a7b604afe1c819093ea4c0837915bd2 completed Aug. 11, 2026, 5:47 p.m.
Created at: April 27, 2026, 11:37 a.m.