Triple

T2286388
Position Surface form Disambiguated ID Type / Status
Subject Tigray Region E51399 entity
Predicate containsTown P847 FINISHED
Object Shire E252968 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: Shire | Statement: [Tigray Region, containsTown, Shire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shire
Context triple: [Tigray Region, containsTown, Shire]
  • A. Shire chosen
    Shire is a town in Ethiopia’s northern Tigray Region, known as a local administrative and commercial center and for its proximity to historic sites such as Axum.
  • B. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • C. Lonza
    Lonza is a global Swiss-based life sciences company specializing in pharmaceutical, biotech, and nutrition products and services, particularly in contract development and manufacturing.
  • D. Novartis
    Novartis is a global Swiss-based pharmaceutical company known for developing innovative medicines across a wide range of therapeutic areas.
  • E. AstraZeneca
    AstraZeneca is a global biopharmaceutical company known for researching, developing, and manufacturing prescription medicines across areas such as oncology, cardiovascular, respiratory, and immunology.
  • 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_69a88b09c644819090b503456d96bf70 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc24730208190af8a5cf443d334f7 completed March 7, 2026, 6:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae894f9ff881909d1b3a7956d82576 completed March 9, 2026, 8:48 a.m.
Created at: March 4, 2026, 7:48 p.m.