Triple

T9257770
Position Surface form Disambiguated ID Type / Status
Subject SABIC E222488 entity
Predicate abbreviation P43 FINISHED
Object SABIC E222488 NE FINISHED

How this triple was built (2 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: SABIC | Statement: [SABIC, abbreviation, SABIC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SABIC
Context triple: [SABIC, abbreviation, SABIC]
  • A. SABIC chosen
    SABIC is a major Saudi-based global petrochemicals and plastics manufacturer known as one of the world’s largest chemical companies.
  • B. BASF
    BASF is a major German chemical company and one of the world's largest producers of chemicals and related products.
  • C. Lanxess
    Lanxess is a German specialty chemicals company known for producing high-performance plastics, rubber, and chemical intermediates for various industrial applications.
  • D. Ineos
    Ineos is a large multinational chemicals and energy company based in the United Kingdom, known for its extensive portfolio of petrochemical, oil, gas, and manufacturing operations worldwide.
  • E. Invista
    Invista is a global manufacturer of polymers and fibers, best known for producing materials used in textiles, carpets, and industrial applications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca841e4cd481908e738c74e958eaea completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd06b660448190b6bc04beff0f5512 completed April 1, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69d09bf225608190ade085302946dd8f completed April 4, 2026, 5:04 a.m.
Created at: March 30, 2026, 7:32 p.m.