Triple

T27293578
Position Surface form Disambiguated ID Type / Status
Subject Shau Kei Wan E688695 entity
Predicate hasPublicHousingEstate P12192 FINISHED
Object Yiu Tung Estate
Yiu Tung Estate is a public housing estate in Shau Kei Wan, Hong Kong, providing high-density residential accommodation for lower- and middle-income residents.
E1772662 NE FINISHED

How this triple was built (2 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: Yiu Tung Estate | Statement: [Shau Kei Wan, hasPublicHousingEstate, Yiu Tung Estate]
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: Yiu Tung Estate
Triple: [Shau Kei Wan, hasPublicHousingEstate, Yiu Tung Estate]
Generated description
Yiu Tung Estate is a public housing estate in Shau Kei Wan, Hong Kong, providing high-density residential accommodation for lower- and middle-income residents.

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_69ef355a96308190a2bed991525fb278 completed April 27, 2026, 10:07 a.m.
NER Named-entity recognition batch_69f6277e806c819085dbcbddb9d86af1 completed May 2, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12b228ee1c8190931374c07c136559 completed May 24, 2026, 8:09 a.m.
NEDg Description generation batch_6a12b34db36c81908d6f05b3e610013a completed May 24, 2026, 8:14 a.m.
NED2 Entity disambiguation (via description) batch_6a12b42bd380819087489bdeb2dbfab7 completed May 24, 2026, 8:17 a.m.
Created at: April 27, 2026, 11:17 a.m.