Triple

T16892585
Position Surface form Disambiguated ID Type / Status
Subject Chance Combs E424211 entity
Predicate sibling P363 FINISHED
Object Christian Combs E421075 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: Christian Combs | Statement: [Chance Combs, sibling, Christian Combs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christian Combs
Context triple: [Chance Combs, sibling, Christian Combs]
  • A. Christian Combs chosen
    Christian Combs, also known as King Combs, is an American rapper, model, and the son of music mogul Sean "Diddy" Combs.
  • B. Greg Corbin
    Greg Corbin is a character from the animated television series "American Dad!", known as Stan Smith’s liberal, openly gay neighbor and local news anchor.
  • C. Ryan McCombs
    Ryan McCombs is an American rock vocalist best known as the former lead singer of the metal band Drowning Pool and later of SOiL.
  • D. Daniel Appling
    Daniel Appling was a United States Army officer and hero of the War of 1812 from Georgia.
  • E. Nicholas Clinch
    Nicholas Clinch was an American mountaineer and expedition leader best known for leading the first ascent of Antarctica’s highest peak, Vinson Massif.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc6b97c8190b18aca477d6ef647 completed April 18, 2026, 5:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7a7fd8481908ef82a13418b1c2d completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:29 a.m.