Triple

T22149343
Position Surface form Disambiguated ID Type / Status
Subject Perkin & Sons E547372 entity
Predicate basedOnDiscoveryOf P133312 FINISHED
Object mauveine NE NERFINISHED

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: mauveine | Statement: [Perkin & Sons, basedOnDiscoveryOf, mauveine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: mauveine
Context triple: [Perkin & Sons, basedOnDiscoveryOf, mauveine]
  • A. Mazarine
    Mazarine is a French writer, academic, and media figure best known as the once-secret daughter of former French President François Mitterrand.
  • B. Vijoličasti
    Vijoličasti is the popular nickname for Slovenian football club NK Maribor, referring to their distinctive purple team colors.
  • C. Violette
    Violette is a small river in France that serves as a tributary of the Alagnon.
  • D. Bleu noir
    Bleu noir is a 2010 studio album by French singer-songwriter Mylène Farmer that blends pop, electronic, and dark atmospheric influences.
  • E. Gamay Noir
    Gamay Noir is a red wine grape variety best known for producing light-bodied, fruit-forward wines such as those from France’s Beaujolais region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: mauveine
Target entity description: Mauveine is the first synthetic aniline dye, historically significant for launching the modern chemical dye industry and revolutionizing textile coloration in the mid-19th century.
  • A. Mazarine
    Mazarine is a French writer, academic, and media figure best known as the once-secret daughter of former French President François Mitterrand.
  • B. Vijoličasti
    Vijoličasti is the popular nickname for Slovenian football club NK Maribor, referring to their distinctive purple team colors.
  • C. Violette
    Violette is a small river in France that serves as a tributary of the Alagnon.
  • D. Bleu noir
    Bleu noir is a 2010 studio album by French singer-songwriter Mylène Farmer that blends pop, electronic, and dark atmospheric influences.
  • E. Gamay Noir
    Gamay Noir is a red wine grape variety best known for producing light-bodied, fruit-forward wines such as those from France’s Beaujolais region.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: basedOnDiscoveryOf
Context triple: [Perkin & Sons, basedOnDiscoveryOf, mauveine]
  • A. madeDiscoveryOn
    Indicates that an entity discovered or identified something on a specific date or at a specific point in time.
  • B. discoveredAs
    Indicates that one entity was first identified, found, or recognized in the role or form specified by another entity.
  • C. inspiredDiscoveryOf chosen
    Indicates that one entity’s ideas, actions, or work motivated or led directly to another entity’s discovery.
  • D. isDiscoveredBy
    Indicates that something (such as an object, fact, or phenomenon) is found, identified, or revealed by a particular agent or entity.
  • E. wasDiscoveredAt
    Indicates that an entity was found, identified, or uncovered at a specific place or during a particular event or context.
  • F. None of above.

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_69e11e3b52088190ad5df386d01eb2fb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129f2c0e881909c3488bb5eb5959d completed April 28, 2026, 9:43 p.m.
PD Predicate disambiguation batch_69e71b384e008190b723c9a0f1089d66 completed April 21, 2026, 6:37 a.m.
Created at: April 16, 2026, 8:33 p.m.