Triple

T23611529
Position Surface form Disambiguated ID Type / Status
Subject American Idol (season 5) E583050 entity
Predicate contestant P46216 FINISHED
Object Kevin Covais
Kevin Covais is an American singer and actor who gained national recognition as a teenage finalist on the fifth season of the television talent show American Idol.
E1595308 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: Kevin Covais | Statement: [American Idol (season 5), contestant, Kevin Covais]
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: Kevin Covais
Triple: [American Idol (season 5), contestant, Kevin Covais]
Generated description
Kevin Covais is an American singer and actor who gained national recognition as a teenage finalist on the fifth season of the television talent show American Idol.

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_69e248fbcd9081908ba08913f9d30826 completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1b0f4606881908207114c5bcfe6a6 completed April 29, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f459017f88190b6cdca1d68683cd9 completed May 21, 2026, 5:49 p.m.
NEDg Description generation batch_6a0f47abc0fc8190be73544bf1879295 completed May 21, 2026, 5:58 p.m.
NED2 Entity disambiguation (via description) batch_6a0f482e4f7c81908dd9930933aac363 completed May 21, 2026, 6 p.m.
Created at: April 17, 2026, 6:45 p.m.