Triple

T12452402
Position Surface form Disambiguated ID Type / Status
Subject Surf E297561 entity
Predicate competitor P1375 FINISHED
Object Ariel
Ariel is a well-known laundry detergent brand marketed as a major global competitor in the fabric care industry.
E348409 NE FINISHED

How this triple was built (4 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: Ariel | Statement: [Surf, competitor, Ariel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ariel
Context triple: [Surf, competitor, Ariel]
  • A. Ariel
    Ariel is a posthumously published poetry collection by Sylvia Plath that is widely regarded as her most powerful and influential work.
  • B. Ariel
    Ariel is one of Uranus's major icy moons, known for its relatively bright surface and complex system of canyons and fault valleys.
  • C. Ariel
    Ariel "Ari" Emanuel is a prominent American talent agent and entertainment executive, best known as the CEO of Endeavor and a major power broker in Hollywood.
  • D. Ariel
    Ariel is a large Israeli settlement city in the central West Bank, known for its significant population, industrial zone, and the presence of Ariel University.
  • E. Ariel
    Ariel is a spirit of the air and a central supernatural character in William Shakespeare’s play "The Tempest."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Ariel
Triple: [Surf, competitor, Ariel]
Generated description
Ariel is a well-known laundry detergent brand marketed as a major global competitor in the fabric care industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ariel
Target entity description: Ariel is a well-known laundry detergent brand marketed as a major global competitor in the fabric care industry.
  • A. Ariel chosen
    Ariel is a leading global laundry detergent brand known for its stain-removal performance and wide range of fabric care products.
  • B. Ariel
    Ariel is a large Israeli settlement city in the central West Bank, known for its significant population, industrial zone, and the presence of Ariel University.
  • C. Ariel
    Ariel is a given name commonly used for both males and females, originating from Hebrew and often associated with meanings like "lion of God."
  • D. Ariel
    Ariel is a central character in the darkly comic Broadway play "The Pillowman," serving as one of the interrogators whose brutal methods and complex morality drive much of the drama.
  • E. Ariel
    Ariel is one of Uranus's major icy moons, known for its relatively bright surface and complex system of canyons and fault valleys.
  • F. None of above.

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_69d6ada166c48190b902972cd2408fa3 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94da0b5988190b9df26dd3bb87337 completed April 10, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f16e87c8190b7e9f61561ae865a completed May 2, 2026, 6:14 p.m.
NEDg Description generation batch_69f6412345ac8190826f4fecb8055fb5 completed May 2, 2026, 6:23 p.m.
NED2 Entity disambiguation (via description) batch_69f64231606481909b8dd9d878670a6c completed May 2, 2026, 6:28 p.m.
Created at: April 8, 2026, 9:56 p.m.