Triple

T27009396
Position Surface form Disambiguated ID Type / Status
Subject Lush Life E680342 entity
Predicate songwriter P1141 FINISHED
Object Linnea Södahl
Linnea Södahl, better known by her stage name Zara Larsson’s frequent collaborator, is a Swedish singer-songwriter recognized for co-writing international pop hits including “Lush Life.”
E1763482 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: Linnea Södahl | Statement: [Lush Life, songwriter, Linnea Södahl]
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: Linnea Södahl
Triple: [Lush Life, songwriter, Linnea Södahl]
Generated description
Linnea Södahl, better known by her stage name Zara Larsson’s frequent collaborator, is a Swedish singer-songwriter recognized for co-writing international pop hits including “Lush Life.”

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_69eeeb53939c8190bd431f32b060f01f completed April 27, 2026, 4:51 a.m.
NER Named-entity recognition batch_69f621d5c0008190a89484d5d970ecb2 completed May 2, 2026, 4:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a126252f0608190900afd2ca4aa27df completed May 24, 2026, 2:28 a.m.
NEDg Description generation batch_6a12687efbb48190b57911fe1c213841 completed May 24, 2026, 2:54 a.m.
NED2 Entity disambiguation (via description) batch_6a12693d12e081909a7005350897e621 completed May 24, 2026, 2:58 a.m.
Created at: April 27, 2026, 7:02 a.m.