Triple
T37145972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laurent-Désiré Kabila |
E920239
|
entity |
| Predicate | capitalOfCountryDuringPresidency |
P29979
|
FINISHED |
| Object | Kinshasa |
—
|
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: Kinshasa | Statement: [Laurent-Désiré Kabila, capitalOfCountryDuringPresidency, Kinshasa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfCountryDuringPresidency Context triple: [Laurent-Désiré Kabila, capitalOfCountryDuringPresidency, Kinshasa]
-
A.
countryLedDuringPresidency
Indicates that a person held the office of president of a specified country and served as its leader during their presidential term.
-
B.
servedAsCapitalDuring
chosen
Indicates that a place functioned as the official capital of a political entity during a specified time period.
-
C.
servedAsUSCapitalFrom
Indicates that a location functioned as the capital of the United States during a specified time period.
-
D.
hasCapitalCityAsPresident
Indicates that a capital city serves as the seat or location of the president’s official residence or primary office.
-
E.
builtDuringPresidencyOf
Indicates that the construction of something occurred while a specified person was serving as president.
- 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fdee770af48190aca2670db50f8b49 |
completed | May 8, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69fdecec98a08190a357d816dc2a6dbe |
completed | May 8, 2026, 2:02 p.m. |
Created at: May 3, 2026, 4:15 p.m.