Triple
T25161647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sistema Interamericano de Derechos Humanos |
E626453
|
entity |
| Predicate | tieneSedePrincipal |
P162988
|
FINISHED |
| Object | San José de Costa Rica |
—
|
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: San José de Costa Rica | Statement: [Sistema Interamericano de Derechos Humanos, tieneSedePrincipal, San José de Costa Rica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tieneSedePrincipal Context triple: [Sistema Interamericano de Derechos Humanos, tieneSedePrincipal, San José de Costa Rica]
-
A.
tieneSedePrincipal
chosen
Indicates that an entity has its main headquarters or principal office located in a specified place.
-
B.
hasHeadquartersFunctionFor
Indicates that an entity serves as the central coordinating or managing headquarters for another entity’s operations or activities.
-
C.
hasHeadquartersRoleFor
Indicates that an entity holds a specific role or position within the headquarters of another entity.
-
D.
hasHeadquartersType
Indicates the specific kind or classification of headquarters associated with an entity.
-
E.
hasHeadquartersOn
Indicates that an organization’s main headquarters is located on a specified street, road, or similar thoroughfare.
- 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_69e2ff2834ec8190b0872e2ec3d76023 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 18, 2026, 6:31 a.m.