Triple

T22919008
Position Surface form Disambiguated ID Type / Status
Subject Mondelez International E568804 entity
Predicate brand P1500 FINISHED
Object Lacta
Lacta is a popular chocolate and confectionery brand owned by Mondelēz International, known especially in markets like Brazil and Greece for its milk chocolate products.
 E1561843 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: Lacta | Statement: [Mondelez International, brand, Lacta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lacta
Context triple: [Mondelez International, brand, Lacta]
  • A. Lactodorum
    Lactodorum is the Roman-era name for the town now known as Towcester in Northamptonshire, England.
  • B. Leite
    Leite is a Portuguese-language surname commonly found in Brazil and other Lusophone countries.
  • C. Milch
    Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
  • D. Labenne
    Labenne is a coastal commune in southwestern France, known for its Atlantic beaches and location in the Landes department of the Nouvelle-Aquitaine region.
  • E. Colla
    The Colla are an indigenous Aymara-speaking people of the Andean highlands, historically inhabiting the region that formed part of the Inca Empire’s Collasuyu.
  • 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: Lacta
Triple: [Mondelez International, brand, Lacta]
Generated description
Lacta is a popular chocolate and confectionery brand owned by Mondelēz International, known especially in markets like Brazil and Greece for its milk chocolate products.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lacta
Target entity description: Lacta is a popular chocolate and confectionery brand owned by Mondelēz International, known especially in markets like Brazil and Greece for its milk chocolate products.
  • A. Lactodorum
    Lactodorum is the Roman-era name for the town now known as Towcester in Northamptonshire, England.
  • B. Leite
    Leite is a Portuguese-language surname commonly found in Brazil and other Lusophone countries.
  • C. Milch
    Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
  • D. Labenne
    Labenne is a coastal commune in southwestern France, known for its Atlantic beaches and location in the Landes department of the Nouvelle-Aquitaine region.
  • E. Colla
    The Colla are an indigenous Aymara-speaking people of the Andean highlands, historically inhabiting the region that formed part of the Inca Empire’s Collasuyu.
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180d316188190901d9356c07110e3 completed April 29, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bc242d8188190b8c4fba17337d787 completed May 19, 2026, 1:52 a.m.
NEDg Description generation batch_6a0bc2ea198081909fac3f91b13e444d completed May 19, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_6a0bc36ee72c81908bb65de9d23a2c13 completed May 19, 2026, 1:57 a.m.
Created at: April 17, 2026, 3:42 p.m.