Triple

T37836582
Position Surface form Disambiguated ID Type / Status
Subject South Caucasus Pipeline E943353 entity
Predicate sourceField P58693 FINISHED
Object Shah Deniz gas field
Shah Deniz gas field is a major natural gas and condensate field in the Caspian Sea off Azerbaijan, serving as a key source for regional and European gas supplies.
 E2245714 NE FINISHED

How this triple was built (3 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: Shah Deniz gas field | Statement: [South Caucasus Pipeline, sourceField, Shah Deniz gas field]
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: Shah Deniz gas field
Triple: [South Caucasus Pipeline, sourceField, Shah Deniz gas field]
Generated description
Shah Deniz gas field is a major natural gas and condensate field in the Caspian Sea off Azerbaijan, serving as a key source for regional and European gas supplies.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: sourceField
Context triple: [South Caucasus Pipeline, sourceField, Shah Deniz gas field]
  • A. keyFieldSource
    Indicates that one field serves as the originating or primary source for a key value used to identify or link related data.
  • B. source
    Indicates that something originates from, is derived from, or is provided by a particular entity or location.
  • C. fromField chosen
    Indicates that something originates in, is sourced from, or is associated with a particular field or domain.
  • D. sourceCategory
    Indicates the classification or type from which something originates or is derived.
  • E. targetsField
    Indicates that one entity is directed toward, focuses on, or is intended to affect a specific field or attribute of another entity.
  • F. None of above.

Provenance (6 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_69f76eeb0f7081908d6d3adbc469889c completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fcdf2394748190b35cead3e208447d completed May 7, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40fb858c688190a3c762068bf97993 completed June 28, 2026, 10:46 a.m.
NEDg Description generation batch_6a40fc1014b481909d49228689c8a7d7 completed June 28, 2026, 10:48 a.m.
NED2 Entity disambiguation (via description) batch_6a40fd1546c081909e9ceebadb9ef51a completed June 28, 2026, 10:53 a.m.
PD Predicate disambiguation batch_69fcdbe344ec8190a0471911952f4b82 completed May 7, 2026, 6:37 p.m.
Created at: May 3, 2026, 4:19 p.m.