Triple
T26768251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Bourke, 1st Baron Connemara |
E675002
|
entity |
| Predicate | continentOfOfficeJurisdiction |
P70311
|
FINISHED |
| Object | Asia |
—
|
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: Asia | Statement: [Robert Bourke, 1st Baron Connemara, continentOfOfficeJurisdiction, Asia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: continentOfOfficeJurisdiction Context triple: [Robert Bourke, 1st Baron Connemara, continentOfOfficeJurisdiction, Asia]
-
A.
continentOfOffice
Indicates the continent on which a given office is geographically located.
-
B.
continentOfGoverningBody
Indicates the continent on which the governing body responsible for a given entity is located.
-
C.
continentOfGovernedTerritory
chosen
Indicates that a governing entity’s jurisdiction lies within a territory located on a specified continent.
-
D.
countryOfJurisdiction
Indicates the country whose legal authority or jurisdiction governs or applies to a given entity, action, or arrangement.
-
E.
countryJurisdiction
Indicates that one country has legal authority, control, or governing power over a specified territory, entity, or matter.
- 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_69eecda85298819097ee1c38a3d772e7 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 27, 2026, 4:01 a.m.