Triple
T24850471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government House, Port Louis |
E621871
|
entity |
| Predicate | capitalOfCountryLocation |
P37327
|
FINISHED |
| Object | Port Louis |
—
|
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: Port Louis | Statement: [Government House, Port Louis, capitalOfCountryLocation, Port Louis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfCountryLocation Context triple: [Government House, Port Louis, capitalOfCountryLocation, Port Louis]
-
A.
countryCapitalLocatedOn
Indicates that the capital city of a country is situated on or directly adjacent to a specified geographic feature (such as a river, coast, or lake).
-
B.
capitalOfCountryLocatedOn
Indicates that a city serves as the capital of a country that is geographically located on a specified landmass or region.
-
C.
countryCapitalOfLocatedCity
Indicates that a city serves as the capital of a country and is geographically located within that country.
-
D.
capitalLocation
chosen
Indicates the relationship in which a place serves as the capital city or administrative center of a given political or geographic entity.
-
E.
countryCapitalLocatedIn
Indicates that the capital city of a country is geographically situated within that country.
- 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_69e2fac297e481909d3aedc75f585e42 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f43043512481909501a3979cac9947 |
completed | May 1, 2026, 4:46 a.m. |
| PD | Predicate disambiguation | batch_69f420fd375c81908ea4a4e60b76ee8f |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:20 a.m.