Triple

T28261040
Position Surface form Disambiguated ID Type / Status
Subject Lakmé E712582 entity
Predicate characterRole P268 FINISHED
Object Lakmé is a Hindu priest's daughter
Lakmé is the title character and soprano heroine of Léo Delibes’ French opera, known for her lyrical beauty and the famous “Flower Duet.”
 E1811608 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: Lakmé is a Hindu priest's daughter | Statement: [Lakmé, characterRole, Lakmé is a Hindu priest's daughter]
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: Lakmé is a Hindu priest's daughter
Triple: [Lakmé, characterRole, Lakmé is a Hindu priest's daughter]
Generated description
Lakmé is the title character and soprano heroine of Léo Delibes’ French opera, known for her lyrical beauty and the famous “Flower Duet.”

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_69efb5207eb08190827e4c34048030b1 completed April 27, 2026, 7:12 p.m.
NER Named-entity recognition batch_69f644190b30819098d7d6d839f9b449 completed May 2, 2026, 6:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1607173b78819082a359d96a70770a completed May 26, 2026, 8:48 p.m.
NEDg Description generation batch_6a161433b69c81909fdd10b625bcfb9d completed May 26, 2026, 9:44 p.m.
NED2 Entity disambiguation (via description) batch_6a16149e8dd48190996fb7f0f32fb031 completed May 26, 2026, 9:46 p.m.
Created at: April 27, 2026, 11:11 p.m.