Triple

T38190600
Position Surface form Disambiguated ID Type / Status
Subject Ho Man Tin E1005448 entity
Predicate hasFacility P105 FINISHED
Object Ho Man Tin Government Offices
Ho Man Tin Government Offices is a government complex in the Ho Man Tin area of Hong Kong that houses various public administration departments and services.
E2259995 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: Ho Man Tin Government Offices | Statement: [Ho Man Tin, hasFacility, Ho Man Tin Government Offices]
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: Ho Man Tin Government Offices
Triple: [Ho Man Tin, hasFacility, Ho Man Tin Government Offices]
Generated description
Ho Man Tin Government Offices is a government complex in the Ho Man Tin area of Hong Kong that houses various public administration departments and services.

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_69f76dbd22f48190940318cea061e8bb completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69fcb117bed4819096b1b56e00f05a4b completed May 7, 2026, 3:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a417b3fae14819083c6191c451d97fd completed June 28, 2026, 7:51 p.m.
NEDg Description generation batch_6a417cd7acc88190bd7681188167ea06 completed June 28, 2026, 7:58 p.m.
NED2 Entity disambiguation (via description) batch_6a417d439728819098feaa986cae3336 completed June 28, 2026, 8 p.m.
Created at: May 3, 2026, 4:29 p.m.