Triple

T13538157
Position Surface form Disambiguated ID Type / Status
Subject Arkema E323313 entity
Predicate notableBrand P1500 FINISHED
Object Bostik
Bostik is a global adhesive and sealant manufacturer known for its products used in construction, industrial, and consumer markets.
 E1048563 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: Bostik | Statement: [Arkema, notableBrand, Bostik]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bostik
Context triple: [Arkema, notableBrand, Bostik]
  • A. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • B. Rilsan
    Rilsan is a high-performance bio-based polyamide (nylon) material widely used for its durability, chemical resistance, and flexibility in demanding industrial applications.
  • C. Viewliner
    Viewliner is a class of single-level passenger railcars used primarily by Amtrak for long-distance overnight service in the United States.
  • D. Glue
    "Glue" is a novel by Scottish author Irvine Welsh that follows the intertwined lives of four working-class friends in Edinburgh over several decades.
  • E. LouSeal
    LouSeal is the playful seal mascot of the Columbus Clippers minor league baseball team, entertaining fans at games in Columbus, Ohio.
  • 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: Bostik
Triple: [Arkema, notableBrand, Bostik]
Generated description
Bostik is a global adhesive and sealant manufacturer known for its products used in construction, industrial, and consumer markets.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bostik
Target entity description: Bostik is a global adhesive and sealant manufacturer known for its products used in construction, industrial, and consumer markets.
  • A. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • B. Rilsan
    Rilsan is a high-performance bio-based polyamide (nylon) material widely used for its durability, chemical resistance, and flexibility in demanding industrial applications.
  • C. Viewliner
    Viewliner is a class of single-level passenger railcars used primarily by Amtrak for long-distance overnight service in the United States.
  • D. Glue
    "Glue" is a novel by Scottish author Irvine Welsh that follows the intertwined lives of four working-class friends in Edinburgh over several decades.
  • E. LouSeal
    LouSeal is the playful seal mascot of the Columbus Clippers minor league baseball team, entertaining fans at games in Columbus, Ohio.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafbe39948190808062d4eff91841 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76babfb948190bc028450ddaa0b72 completed May 3, 2026, 3:37 p.m.
NEDg Description generation batch_69f77640b5308190aaa50e8d5d871832 completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f778f01700819099c3e9cbc84f29e4 completed May 3, 2026, 4:33 p.m.
Created at: April 9, 2026, 9:45 p.m.