Triple
T26014736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empresa Colombiana de Sal |
E646994
|
entity |
| Predicate | sharesBorderWithSector |
P180114
|
FINISHED |
| Object | public sector |
—
|
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: public sector | Statement: [Empresa Colombiana de Sal, sharesBorderWithSector, public sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesBorderWithSector Context triple: [Empresa Colombiana de Sal, sharesBorderWithSector, public sector]
-
A.
sharesBorderWithDepartment
Indicates that one administrative department directly borders or touches the territorial boundary of another department.
-
B.
sharesBorderWithOffice
Indicates that one entity’s boundary directly adjoins or touches the boundary of an office.
-
C.
shareBorderAgreement
Indicates that two entities have a formally recognized agreement concerning their shared border.
-
D.
linkedSector
Indicates that one sector is associated or connected to another sector in a meaningful or relevant way.
-
E.
sharesSectionsWith
Indicates that two entities have one or more sections or segments in common.
- 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_69e77e8aa65881909ca58918f29ab2a0 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f73223675481908c1bc3208c0f5284 |
completed | May 3, 2026, 11:31 a.m. |
| PD | Predicate disambiguation | batch_69f7317690108190b3aae2cd2e1d069e |
completed | May 3, 2026, 11:28 a.m. |
| PDg | Predicate description generation | batch_69f73221eef88190bd8905e6e9f5a586 |
completed | May 3, 2026, 11:31 a.m. |
Created at: April 22, 2026, 9:03 a.m.