Triple
T1588288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brasília |
E34115
|
entity |
| Predicate | IBGECode |
P30029
|
FINISHED |
| Object | 5300108 |
—
|
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: 5300108 | Statement: [Brasília, IBGECode, 5300108]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: IBGECode Context triple: [Brasília, IBGECode, 5300108]
-
A.
metroArea
Indicates that one location is part of, or belongs to, a specified metropolitan area.
-
B.
inseeCode
Indicates the official INSEE (French national statistics institute) code assigned to an entity, typically identifying a specific geographic or administrative unit.
-
C.
gdpCharacteristic
Indicates a characteristic, attribute, or qualitative aspect associated with a country’s or region’s gross domestic product (GDP).
-
D.
taxId
Indicates that an entity is associated with a specific taxonomic identifier used to uniquely reference its position in a taxonomic classification system.
-
E.
FIPSCode
Indicates the standardized Federal Information Processing Standards (FIPS) code assigned to identify a specific geographic or administrative entity.
- F. None of above. chosen
Provenance (4 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_69a885fceb2c8190b47e0f7c0aefbff0 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93aedd45c819085843ac843d640e8 |
completed | March 5, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69a907bdc19081908c84c5c0aa09e282 |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a93aec7dc481909375726fbfb9e272 |
completed | March 5, 2026, 8:12 a.m. |
Created at: March 4, 2026, 7:27 p.m.