Triple

T11603369
Position Surface form Disambiguated ID Type / Status
Subject Żejtun E275187 entity
Predicate hasSubdivision P747 FINISHED
Object Bulebel
Bulebel is an industrial and residential area forming part of the town of Żejtun in Malta.
 E936343 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: Bulebel | Statement: [Żejtun, hasSubdivision, Bulebel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bulebel
Context triple: [Żejtun, hasSubdivision, Bulebel]
  • A. Biloela
    Biloela is a rural town in Queensland, Australia, known as an agricultural and administrative centre for the surrounding Central Queensland region.
  • B. Lefua
    Lefua is a genus of small freshwater loaches native to East Asia, known for inhabiting cool, clear streams and belonging to the stone loach family.
  • C. Enbilulu
    Enbilulu is a Mesopotamian deity associated with irrigation, canals, and the management of rivers and agricultural waters.
  • D. Behati
    Behati is a Namibian-born fashion model best known for her work as a Victoria’s Secret Angel and her high-profile presence in the international modeling industry.
  • E. Dondo
    Dondo is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • 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: Bulebel
Triple: [Żejtun, hasSubdivision, Bulebel]
Generated description
Bulebel is an industrial and residential area forming part of the town of Żejtun in Malta.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bulebel
Target entity description: Bulebel is an industrial and residential area forming part of the town of Żejtun in Malta.
  • A. Biloela
    Biloela is a rural town in Queensland, Australia, known as an agricultural and administrative centre for the surrounding Central Queensland region.
  • B. Lefua
    Lefua is a genus of small freshwater loaches native to East Asia, known for inhabiting cool, clear streams and belonging to the stone loach family.
  • C. Enbilulu
    Enbilulu is a Mesopotamian deity associated with irrigation, canals, and the management of rivers and agricultural waters.
  • D. Behati
    Behati is a Namibian-born fashion model best known for her work as a Victoria’s Secret Angel and her high-profile presence in the international modeling industry.
  • E. Dondo
    Dondo is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d895502e0081909ee9c3d45d26cd91 completed April 10, 2026, 6:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69e8a8022800819096d7a87ac8c1c751 completed April 22, 2026, 10:50 a.m.
NEDg Description generation batch_69e8af9665648190b7732076aa129671 completed April 22, 2026, 11:23 a.m.
NED2 Entity disambiguation (via description) batch_69ee5b3a3720819095a4a87176e052cb completed April 26, 2026, 6:36 p.m.
Created at: April 8, 2026, 9:38 p.m.