Triple
T562213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nouakchott |
E13475
|
entity |
| Predicate | hasGovernmentBuildings |
P9045
|
FINISHED |
| Object | presidential palace |
—
|
LITERAL FINISHED |
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: presidential palace | Statement: [Nouakchott, hasGovernmentBuildings, presidential palace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGovernmentBuildings Context triple: [Nouakchott, hasGovernmentBuildings, presidential palace]
-
A.
hasLegislatureBuilding
Indicates that one entity serves as the official legislature building or physical premises where the legislative body of another entity meets or operates.
-
B.
hasCityHall
Indicates that a location or administrative area possesses or is served by a specific city hall building or institution.
-
C.
isGovernmentFacility
chosen
Indicates that the subject entity functions as a facility owned, operated, or officially designated for use by a government or its agencies.
-
D.
hasHeadquartersBuilding
Indicates that an organization possesses a specific building that serves as its headquarters location.
-
E.
stateCapitalBuilding
Indicates that a building serves as the primary governmental capitol facility for a specific state.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49a700e608190b235246df057bd9b |
completed | March 1, 2026, 7:58 p.m. |
| PD | Predicate disambiguation | batch_69a494c044648190a98589ab18935216 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.