Triple

T16067451
Position Surface form Disambiguated ID Type / Status
Subject Aisin Corporation E389767 entity
Predicate hasBrand P1500 FINISHED
Object AISIN
AISIN is a global automotive parts brand known for manufacturing high-quality components such as transmissions, brakes, and engine-related systems for major vehicle manufacturers.
 E1193301 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: AISIN | Statement: [Aisin Corporation, hasBrand, AISIN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AISIN
Context triple: [Aisin Corporation, hasBrand, AISIN]
  • A. Aisai
    Aisai is a city in central Japan known for its agricultural landscape and location within Aichi Prefecture near the Nagoya metropolitan area.
  • B. Ais
    The Ais were a Native American people who inhabited the Atlantic coast of what is now central and southeastern Florida prior to European colonization.
  • C. Aoto
    Aoto is a neighborhood in Tokyo, Japan, located within Katsushika Ward and known as a residential and commercial area with convenient rail access.
  • D. Toyo
    Toyo is a neighborhood and administrative district located within Kōtō Ward in Tokyo, Japan.
  • E. Ebara
    Ebara is a district within Tokyo’s Shinagawa ward, known as a primarily residential area with local shopping streets and traditional neighborhoods.
  • 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: AISIN
Triple: [Aisin Corporation, hasBrand, AISIN]
Generated description
AISIN is a global automotive parts brand known for manufacturing high-quality components such as transmissions, brakes, and engine-related systems for major vehicle manufacturers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AISIN
Target entity description: AISIN is a global automotive parts brand known for manufacturing high-quality components such as transmissions, brakes, and engine-related systems for major vehicle manufacturers.
  • A. Aisai
    Aisai is a city in central Japan known for its agricultural landscape and location within Aichi Prefecture near the Nagoya metropolitan area.
  • B. Ais
    The Ais were a Native American people who inhabited the Atlantic coast of what is now central and southeastern Florida prior to European colonization.
  • C. Aoto
    Aoto is a neighborhood in Tokyo, Japan, located within Katsushika Ward and known as a residential and commercial area with convenient rail access.
  • D. Toyo
    Toyo is a neighborhood and administrative district located within Kōtō Ward in Tokyo, Japan.
  • E. Ebara
    Ebara is a district within Tokyo’s Shinagawa ward, known as a primarily residential area with local shopping streets and traditional neighborhoods.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183baf29481908e5c66879e125363 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe480d59c8190962ac596a872b5e0 completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe6ee34788190942ef1d3bb805f78 completed May 10, 2026, 2:01 a.m.
NED2 Entity disambiguation (via description) batch_69ffe7d127848190bbd79a8b94a49f93 completed May 10, 2026, 2:05 a.m.
Created at: April 10, 2026, 4:57 a.m.