Triple
T14916709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | coat of arms of Hong Kong (1959–1997) |
E371400
|
entity |
| Predicate | supporterSinister |
P57637
|
FINISHED |
| Object | Chinese dragon Or |
—
|
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: Chinese dragon Or | Statement: [coat of arms of Hong Kong (1959–1997), supporterSinister, Chinese dragon Or]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supporterSinister Context triple: [coat of arms of Hong Kong (1959–1997), supporterSinister, Chinese dragon Or]
-
A.
hasSupporterSinister
chosen
Indicates that an entity has a heraldic supporter positioned on the left (sinister) side of its shield or emblem.
-
B.
supporter
Indicates a relationship where one entity backs, advocates for, or provides assistance to another entity, often in an ongoing or affiliative way.
-
C.
supporters
Indicates a relationship where one entity backs, endorses, or actively helps another entity, cause, or position.
-
D.
supporterOf
Indicates that one entity backs, advocates for, or provides assistance to another entity, cause, or organization.
-
E.
opponentSupporters
Indicates that the related entities are supporters or backers of opposing sides in a contest, conflict, or competition.
- 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_69d85cc7ea3481908228b5acb7d06f12 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded62038508190946499cd3552990e |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de9a52ba988190a26e268b4ea083ea |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:32 a.m.