Triple
T28653270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | judicial branch of Liberia |
E725257
|
entity |
| Predicate | locationOfHighestCourt |
P13906
|
FINISHED |
| Object | Monrovia |
—
|
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: Monrovia | Statement: [judicial branch of Liberia, locationOfHighestCourt, Monrovia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfHighestCourt Context triple: [judicial branch of Liberia, locationOfHighestCourt, Monrovia]
-
A.
highestCourtOf
Indicates that one entity is the supreme judicial authority or top-level court within the jurisdiction or legal system of another entity.
-
B.
highCourtSeat
chosen
Indicates that a location serves as the official seat or headquarters of a high court.
-
C.
originalJurisdictionOfHighCourt
Indicates that a particular matter or case falls within the High Court’s original jurisdiction to hear and decide it as a court of first instance.
-
D.
countryHighestCourtBuilding
Indicates the building that houses the highest court of a given country.
-
E.
highestCourtOfAppealFor
Indicates that one entity serves as the ultimate judicial authority to which decisions from the other entity can be appealed.
- 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69ff8aff48988190a48a440de8238ef9 |
completed | May 9, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69ff8a780404819082f48ceb21e7fe11 |
completed | May 9, 2026, 7:26 p.m. |
Created at: April 28, 2026, 4:53 a.m.