Triple

T37058977
Position Surface form Disambiguated ID Type / Status
Subject Selinunte E917268 entity
Predicate dedicatedTemple P28305 FINISHED
Object Temple E to Hera
Temple E to Hera is a well-preserved Doric Greek temple at the ancient city of Selinunte in Sicily, renowned for its classical architecture and religious significance.
 E2223762 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: Temple E to Hera | Statement: [Selinunte, dedicatedTemple, Temple E to Hera]
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 E to Hera
Triple: [Selinunte, dedicatedTemple, Temple E to Hera]
Generated description
Temple E to Hera is a well-preserved Doric Greek temple at the ancient city of Selinunte in Sicily, renowned for its classical architecture and religious significance.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: dedicatedTemple
Context triple: [Selinunte, dedicatedTemple, Temple E to Hera]
  • A. mainTemple
    Indicates that one entity serves as the primary or central temple associated with another entity.
  • B. hadTempleDedicatedTo chosen
    Indicates that a temple was formally dedicated in honor of, or for the worship of, a particular entity.
  • C. templeDedicatedBy
    Indicates that a temple was formally dedicated, consecrated, or established by a specific person, group, or authority.
  • D. associatedTemple
    Indicates a relationship where one entity is linked or connected to a particular temple, typically as its relevant or related religious site.
  • E. residesInTemple
    Indicates that one entity lives or dwells within a temple associated with 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_69f76e95fa40819091e14681087ae5e4 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fb34e5576881909394355c8ec6ddd2 completed May 6, 2026, 12:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a406cc118608190ab84c4e35f5ec72e completed June 28, 2026, 12:37 a.m.
NEDg Description generation batch_6a406defac38819086c2585b63b93dde completed June 28, 2026, 12:42 a.m.
NED2 Entity disambiguation (via description) batch_6a406e7763b081908b37db6d670f2084 completed June 28, 2026, 12:44 a.m.
PD Predicate disambiguation batch_69fb2f6171e88190bf1e0ee6a644b6a9 completed May 6, 2026, 12:09 p.m.
Created at: May 3, 2026, 4:14 p.m.