Triple

T10052604
Position Surface form Disambiguated ID Type / Status
Subject Porsche Macan E208782 entity
Predicate trimLevel P11486 FINISHED
Object Macan
The Macan is Porsche’s compact luxury crossover SUV model known for combining sports-car performance with everyday practicality.
 E836981 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: Macan | Statement: [Porsche Macan, trimLevel, Macan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Macan
Context triple: [Porsche Macan, trimLevel, Macan]
  • A. Singa
    Singa is a city in southeastern Sudan that serves as the administrative and economic center of Sennar State along the Blue Nile.
  • B. Tawailia
    Tawailia is an alternate name for the Uma language, an Austronesian language spoken in parts of Indonesia.
  • C. Itliong
    Itliong is the surname of Filipino American labor leader Larry Itliong, known for his pivotal role in the U.S. farm workers’ movement.
  • D. Kangar
    Kangar is the main administrative and commercial center of the Malaysian state of Perlis.
  • E. Kenyah
    The Kenyah are an indigenous Dayak ethnic group of Borneo, traditionally living in the interior highlands and river valleys of Sarawak and neighboring regions, known for their longhouse communities and rich oral traditions.
  • 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: Macan
Triple: [Porsche Macan, trimLevel, Macan]
Generated description
The Macan is Porsche’s compact luxury crossover SUV model known for combining sports-car performance with everyday practicality.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Macan
Target entity description: The Macan is Porsche’s compact luxury crossover SUV model known for combining sports-car performance with everyday practicality.
  • A. Singa
    Singa is a city in southeastern Sudan that serves as the administrative and economic center of Sennar State along the Blue Nile.
  • B. Tawailia
    Tawailia is an alternate name for the Uma language, an Austronesian language spoken in parts of Indonesia.
  • C. Itliong
    Itliong is the surname of Filipino American labor leader Larry Itliong, known for his pivotal role in the U.S. farm workers’ movement.
  • D. Kangar
    Kangar is the main administrative and commercial center of the Malaysian state of Perlis.
  • E. Kenyah
    The Kenyah are an indigenous Dayak ethnic group of Borneo, traditionally living in the interior highlands and river valleys of Sarawak and neighboring regions, known for their longhouse communities and rich oral traditions.
  • 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_69ca836094408190a36a1ea7e9a86fcd completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcf9135bc8190a48a2e5cbafca0cd completed April 2, 2026, 2:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2829e24488190be65cff760850b9e completed April 5, 2026, 3:41 p.m.
NEDg Description generation batch_69d2839311508190a59c1d393cc38785 completed April 5, 2026, 3:45 p.m.
NED2 Entity disambiguation (via description) batch_69d2843fff188190a21ced57523c329a completed April 5, 2026, 3:48 p.m.
Created at: March 30, 2026, 8:56 p.m.