Triple
T36895794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cecil Chao Sze-tsung |
E911884
|
entity |
| Predicate | offerAmount |
P188086
|
FINISHED |
| Object | HK$500 million |
—
|
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: HK$500 million | Statement: [Cecil Chao Sze-tsung, offerAmount, HK$500 million]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offerAmount Context triple: [Cecil Chao Sze-tsung, offerAmount, HK$500 million]
-
A.
offeredAmount
chosen
Indicates the specific quantity or value that one party proposes to give or pay to another in the context of an offer.
-
B.
offering
Indicates that one entity presents or provides something to another entity, typically as a gift, contribution, or proposal.
-
C.
rewardOfferedBy
Indicates that a reward is provided or promised by one entity to another, typically as an incentive or compensation for a specific action or outcome.
-
D.
offerPricePerShare
Indicates the monetary amount proposed or requested for each individual share in a transaction or offer.
-
E.
firstOffered
Indicates that one entity was the earliest or initial provider or proposer of something to another entity or context.
- 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_69f76e841b54819097e7fa768bbc70b2 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe78e545888190a239af1a84280fa0 |
completed | May 8, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69fe7842742081908043eb950ed69f92 |
completed | May 8, 2026, 11:56 p.m. |
Created at: May 3, 2026, 4:13 p.m.