Triple

T16659373
Position Surface form Disambiguated ID Type / Status
Subject Banana Shire E404814 entity
Predicate hasLocality P7943 FINISHED
Object Wowan South
Wowan South is a rural locality within Queensland’s Banana Shire, characterized by its agricultural landscape and small population.
E1230335 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: Wowan South | Statement: [Banana Shire, hasLocality, Wowan South]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wowan South
Context triple: [Banana Shire, hasLocality, Wowan South]
  • A. Wowan East
    Wowan East is a rural locality within Queensland’s Banana Shire, characterized by its agricultural landscape and small population.
  • B. Wowan North
    Wowan North is a rural locality within the Banana Shire region of Central Queensland, Australia.
  • C. Wowan West
    Wowan West is a rural locality within the Banana Shire region of Queensland, Australia.
  • D. Eslanda
    Eslanda was the given name of Eslanda Goode Robeson, an American anthropologist, author, and civil rights activist married to singer and actor Paul Robeson.
  • E. Tandi
    Tandi is a small rural settlement located in Makoni District in eastern Zimbabwe.
  • 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: Wowan South
Triple: [Banana Shire, hasLocality, Wowan South]
Generated description
Wowan South is a rural locality within Queensland’s Banana Shire, characterized by its agricultural landscape and small population.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wowan South
Target entity description: Wowan South is a rural locality within Queensland’s Banana Shire, characterized by its agricultural landscape and small population.
  • A. Wowan East
    Wowan East is a rural locality within Queensland’s Banana Shire, characterized by its agricultural landscape and small population.
  • B. Wowan North
    Wowan North is a rural locality within the Banana Shire region of Central Queensland, Australia.
  • C. Wowan West
    Wowan West is a rural locality within the Banana Shire region of Queensland, Australia.
  • D. Eslanda
    Eslanda was the given name of Eslanda Goode Robeson, an American anthropologist, author, and civil rights activist married to singer and actor Paul Robeson.
  • E. Tandi
    Tandi is a small town in Himachal Pradesh, India, known as a key junction in the Lahaul region where major mountain rivers meet and as a common stopover for travelers in the Himalayas.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37bfcbb6881909c0419174dd017dc completed April 18, 2026, 12:41 p.m.
NED1 Entity disambiguation (via context triple) batch_6a009d2f7ad88190ba85a79154502841 completed May 10, 2026, 2:58 p.m.
NEDg Description generation batch_6a009df9e4ec81909c4c155a026904fe completed May 10, 2026, 3:02 p.m.
NED2 Entity disambiguation (via description) batch_6a009eb209cc819081c5fb2c89583602 completed May 10, 2026, 3:05 p.m.
Created at: April 10, 2026, 5:18 a.m.