Triple

T13223475
Position Surface form Disambiguated ID Type / Status
Subject Selinus E314814 entity
Predicate hasTemple P1191 FINISHED
Object Temple F
Temple F is an ancient Greek Doric temple in the archaeological site of Selinus (Selinunte) in Sicily, notable for its early classical architecture and historical significance.
E1027994 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: Temple F | Statement: [Selinus, hasTemple, Temple F]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Temple F
Context triple: [Selinus, hasTemple, Temple F]
  • A. Temple A
    Temple A is an ancient Italic religious sanctuary located within the archaeological complex of Pietrabbondante in southern Italy.
  • B. Temple 38
    Temple 38 is an ancient Maya ceremonial structure located within the North Acropolis complex at the archaeological site of Tikal in Guatemala.
  • C. Temple
    Temple is a mid-sized city in central Texas known as a regional medical and transportation hub.
  • D. Temple
    "Temple" is a British television drama series produced by Liza Marshall, centered on an underground clinic beneath London where a surgeon treats criminals and desperate patients.
  • E. Temple
    Temple is a historic legal district in central London, renowned for housing the Inns of Court and many barristers’ chambers.
  • 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: Temple F
Triple: [Selinus, hasTemple, Temple F]
Generated description
Temple F is an ancient Greek Doric temple in the archaeological site of Selinus (Selinunte) in Sicily, notable for its early classical architecture and historical significance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Temple F
Target entity description: Temple F is an ancient Greek Doric temple in the archaeological site of Selinus (Selinunte) in Sicily, notable for its early classical architecture and historical significance.
  • A. Temple A
    Temple A is an ancient Italic religious sanctuary located within the archaeological complex of Pietrabbondante in southern Italy.
  • B. Temple 38
    Temple 38 is an ancient Maya ceremonial structure located within the North Acropolis complex at the archaeological site of Tikal in Guatemala.
  • C. Temple
    Temple is a mid-sized city in central Texas known as a regional medical and transportation hub.
  • D. Temple
    "Temple" is a British television drama series produced by Liza Marshall, centered on an underground clinic beneath London where a surgeon treats criminals and desperate patients.
  • E. Temple
    Temple is a historic legal district in central London, renowned for housing the Inns of Court and many barristers’ chambers.
  • 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_69d806affc688190a25b6ccc588e9c72 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf74d708190a61d8ad938653b06 completed April 10, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff24be9881908b96f3e72325e55f completed May 3, 2026, 7:54 a.m.
NEDg Description generation batch_69f7001924d48190af7d430cb258409a completed May 3, 2026, 7:58 a.m.
NED2 Entity disambiguation (via description) batch_69f700cfb43881909c903ec12b15065a completed May 3, 2026, 8:01 a.m.
Created at: April 9, 2026, 9:19 p.m.