Triple
T35151677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Governor of Hong Kong |
E1015008
|
entity |
| Predicate | residenceUsedFrom |
P24903
|
FINISHED |
| Object | Government House, Hong Kong, from 1855 |
—
|
LITERAL 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: Government House, Hong Kong, from 1855 | Statement: [Governor of Hong Kong, residenceUsedFrom, Government House, Hong Kong, from 1855]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residenceUsedFrom Context triple: [Governor of Hong Kong, residenceUsedFrom, Government House, Hong Kong, from 1855]
-
A.
usedAsOfficialResidenceSince
chosen
Indicates that an entity has served as the formally designated official residence of another entity starting from a specified point in time.
-
B.
usedAsHomeUntil
Indicates that something served as a home for an entity up to a specified end time or event.
-
C.
residenceUsedFor
Indicates that a particular residence is used for a specific purpose, function, or activity.
-
D.
usedAtResidence
Indicates that an object, resource, or service is utilized within or for the purposes of a particular residence.
-
E.
usedAsHomeFrom
Indicates that something served as a home or dwelling for a specified entity starting from a particular point in time.
- F. None of above.
Provenance (3 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_69f76ddb3a708190b521ba2970b17178 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78cecd0d08190bcb21d5b53d232e8 |
completed | May 3, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.