Triple

T20318315
Position Surface form Disambiguated ID Type / Status
Subject Sohar Aluminium smelter E492139 entity
Predicate hasShareholder P1553 FINISHED
Object TAQA
TAQA is a major Abu Dhabi-based energy company focused on power generation and water desalination, with investments in utilities and industrial projects across several regions.
 E1424306 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: TAQA | Statement: [Sohar Aluminium smelter, hasShareholder, TAQA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TAQA
Context triple: [Sohar Aluminium smelter, hasShareholder, TAQA]
  • A. TAQ
    TAQ is the station code for Tasqueña, a major terminal station on Mexico City’s Metro system.
  • B. TA2
    TA2 is a UK postal district within the TA (Taunton) postcode area, covering part of Taunton and its surrounding localities in Somerset, England.
  • C. TA1
    TA1 is a UK postal district within the TA (Taunton) postcode area, covering central Taunton and its immediate surroundings in Somerset, England.
  • D. TAZ
    TAZ is the IATA airport code assigned to Dashoguz International Airport in Turkmenistan.
  • E. TARCO
    TARCO is the airline callsign used by Tarco Aviation, a Sudanese carrier operating regional and international passenger flights.
  • 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: TAQA
Triple: [Sohar Aluminium smelter, hasShareholder, TAQA]
Generated description
TAQA is a major Abu Dhabi-based energy company focused on power generation and water desalination, with investments in utilities and industrial projects across several regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TAQA
Target entity description: TAQA is a major Abu Dhabi-based energy company focused on power generation and water desalination, with investments in utilities and industrial projects across several regions.
  • A. TAQ
    TAQ is the station code for Tasqueña, a major terminal station on Mexico City’s Metro system.
  • B. TA2
    TA2 is a UK postal district within the TA (Taunton) postcode area, covering part of Taunton and its surrounding localities in Somerset, England.
  • C. TA1
    TA1 is a UK postal district within the TA (Taunton) postcode area, covering central Taunton and its immediate surroundings in Somerset, England.
  • D. TAZ
    TAZ is the IATA airport code assigned to Dashoguz International Airport in Turkmenistan.
  • E. TARCO
    TARCO is the airline callsign used by Tarco Aviation, a Sudanese carrier operating regional and international passenger flights.
  • 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67789d8108190ae2e134f4b0b0be5 completed April 20, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a086126c9a08190a6dcb30d118a2730 completed May 16, 2026, 12:20 p.m.
NEDg Description generation batch_6a086255182881908eeaa49d34bf3ba5 completed May 16, 2026, 12:25 p.m.
NED2 Entity disambiguation (via description) batch_6a08635869148190992d75a8806f767c completed May 16, 2026, 12:30 p.m.
Created at: April 16, 2026, 11:20 a.m.