Triple

T2439422
Position Surface form Disambiguated ID Type / Status
Subject StuG III E53237 entity
Predicate manufacturer P490 FINISHED
Object MIAG
MIAG (Mühlenbau und Industrie Aktiengesellschaft) was a German industrial company that, among other activities, produced armored fighting vehicles such as the StuG III during World War II.
 E266906 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: MIAG | Statement: [StuG III, manufacturer, MIAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MIAG
Context triple: [StuG III, manufacturer, MIAG]
  • A. MIA
    MIA is the standard three-letter abbreviation used to represent the Miami Marlins Major League Baseball team.
  • B. MIA
    MIA is the UN/LOCODE designation for Miami, a major coastal city and transportation hub in the U.S. state of Florida.
  • C. MIA
    MIA is a major fine arts museum in Minneapolis, Minnesota, known for its extensive global art collections spanning thousands of years.
  • D. MAI
    MAI is the commonly used abbreviation for Romania’s Ministry of Internal Affairs, the government body responsible for internal security, public order, and civil administration.
  • E. Miga
    Miga is one of the official mascots of the 2010 Winter Olympics in Vancouver, depicted as a playful sea bear inspired by orcas and First Nations legends.
  • 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: MIAG
Triple: [StuG III, manufacturer, MIAG]
Generated description
MIAG (Mühlenbau und Industrie Aktiengesellschaft) was a German industrial company that, among other activities, produced armored fighting vehicles such as the StuG III during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MIAG
Target entity description: MIAG (Mühlenbau und Industrie Aktiengesellschaft) was a German industrial company that, among other activities, produced armored fighting vehicles such as the StuG III during World War II.
  • A. MIA
    MIA is the standard three-letter abbreviation used to represent the Miami Marlins Major League Baseball team.
  • B. MIA
    MIA is the UN/LOCODE designation for Miami, a major coastal city and transportation hub in the U.S. state of Florida.
  • C. MIA
    MIA is a major fine arts museum in Minneapolis, Minnesota, known for its extensive global art collections spanning thousands of years.
  • D. MAI
    MAI is the commonly used abbreviation for Romania’s Ministry of Internal Affairs, the government body responsible for internal security, public order, and civil administration.
  • E. Miga
    Miga is one of the official mascots of the 2010 Winter Olympics in Vancouver, depicted as a playful sea bear inspired by orcas and First Nations legends.
  • 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_69ab495b6dac8190ac82661aa1452222 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc9f62ad081909373134c5adf65d9 completed March 7, 2026, 6:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0b0e920819088bd7ee3684c81fe completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef4d2cd3c81908773ac7ff9e4b28d completed March 9, 2026, 4:26 p.m.
NED2 Entity disambiguation (via description) batch_69aef54c3f1c819085019bd8e48d7db7 completed March 9, 2026, 4:29 p.m.
Created at: March 6, 2026, 9:43 p.m.