Triple
T10247171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Libreville |
E240245
|
entity |
| Predicate | handlesExportOf |
P68049
|
FINISHED |
| Object | timber |
—
|
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: timber | Statement: [Port of Libreville, handlesExportOf, timber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: handlesExportOf Context triple: [Port of Libreville, handlesExportOf, timber]
-
A.
handlesExport
chosen
Indicates that an entity is responsible for managing or processing the export of goods, data, or resources from one context or location to another.
-
B.
exportedTo
Indicates that goods, services, or resources are sent out from one entity or region to another for trade or sale.
-
C.
hasExportActivity
Indicates that an entity engages in exporting goods or services to other countries or external markets.
-
D.
isExportable
Indicates that something can be legally and practically transferred or sent out from one jurisdiction, system, or context to another.
-
E.
exportedVia
Indicates that something is sent out or made available to an external destination through a specified medium, channel, or mechanism.
- 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d328272c8190a3548d7f7f38cfc4 |
completed | April 7, 2026, 9:49 a.m. |
| PD | Predicate disambiguation | batch_69d4d1ebd6c88190a1f3f4a72a99d6fe |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:27 a.m.