Triple

T21708234
Position Surface form Disambiguated ID Type / Status
Subject Obelix E535825 entity
Predicate closeFriend P8712 FINISHED
Object Getafix
Getafix is the wise druid of the Asterix comics, known for brewing the magic potion that gives the Gauls their superhuman strength.
 E1498438 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: Getafix | Statement: [Obelix, closeFriend, Getafix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Getafix
Context triple: [Obelix, closeFriend, Getafix]
  • A. Opekta
    Opekta was a German-Dutch company that produced and sold pectin-based gelling agents for making jam, notably managed in its Amsterdam branch by Anne Frank’s father, Otto Frank.
  • B. Optax
    Optax is a gradient processing and optimization library for JAX, providing a flexible collection of composable optimizers and transformations for training machine learning models.
  • C. Andrex
    Andrex is a popular British toilet tissue brand known for its soft paper and iconic Labrador puppy advertising campaigns.
  • D. Re-Mit
    Re-Mit is a 2013 studio album by the influential English post-punk band The Fall, showcasing their characteristic abrasive sound and Mark E. Smith’s idiosyncratic vocals.
  • E. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • 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: Getafix
Triple: [Obelix, closeFriend, Getafix]
Generated description
Getafix is the wise druid of the Asterix comics, known for brewing the magic potion that gives the Gauls their superhuman strength.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Getafix
Target entity description: Getafix is the wise druid of the Asterix comics, known for brewing the magic potion that gives the Gauls their superhuman strength.
  • A. Opekta
    Opekta was a German-Dutch company that produced and sold pectin-based gelling agents for making jam, notably managed in its Amsterdam branch by Anne Frank’s father, Otto Frank.
  • B. Optax
    Optax is a gradient processing and optimization library for JAX, providing a flexible collection of composable optimizers and transformations for training machine learning models.
  • C. Andrex
    Andrex is a popular British toilet tissue brand known for its soft paper and iconic Labrador puppy advertising campaigns.
  • D. Re-Mit
    Re-Mit is a 2013 studio album by the influential English post-punk band The Fall, showcasing their characteristic abrasive sound and Mark E. Smith’s idiosyncratic vocals.
  • E. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • F. None of above. chosen

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_69e0c46b44c0819088ab883ebd44e0e8 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efb5314a288190b4b8347cca15aaa8 completed April 27, 2026, 7:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a24ad3fe88190ad0a240928367700 completed May 17, 2026, 8:27 p.m.
NEDg Description generation batch_6a0a27c5795c81909e41d7e8e1f95e81 completed May 17, 2026, 8:40 p.m.
NED2 Entity disambiguation (via description) batch_6a0a28a016a08190b67eae1e64619b62 completed May 17, 2026, 8:44 p.m.
Created at: April 16, 2026, 6:46 p.m.