Triple
T35814358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purchase of Cyprus from Richard I of England |
E1035314
|
entity |
| Predicate | hasBuyer |
P68063
|
FINISHED |
| Object | Guy of Lusignan |
—
|
NE NERFINISHED |
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: Guy of Lusignan | Statement: [Purchase of Cyprus from Richard I of England, hasBuyer, Guy of Lusignan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuyer Context triple: [Purchase of Cyprus from Richard I of England, hasBuyer, Guy of Lusignan]
-
A.
isPurchasedBy
chosen
Indicates that one entity is bought or acquired in a transaction by another entity.
-
B.
buyer
Indicates a relationship where one entity purchases or acquires goods, services, or rights from another entity in exchange for payment or compensation.
-
C.
hasTrade
Indicates a relationship where one entity engages in or maintains a commercial exchange or trading activity with another entity.
-
D.
hasSoldOver
Indicates that one entity has sold a quantity of something exceeding a specified threshold or the amount sold by another entity.
-
E.
contractBoughtOutBy
Indicates that an existing contract has been terminated or taken over because another party has paid to assume or end its obligations.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: May 3, 2026, 4:06 p.m.