Triple
T37800835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atakpa |
E942368
|
entity |
| Predicate | hasPortFunctionHistorically |
P125751
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Atakpa, hasPortFunctionHistorically, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortFunctionHistorically Context triple: [Atakpa, hasPortFunctionHistorically, yes]
-
A.
hasPortHistory
Indicates that an entity has an associated record or log of its past port-related events, visits, or configurations.
-
B.
hasPortFunctionVia
Indicates that an entity possesses a port or interface that fulfills a specific function by means of, or through, another related element or mechanism.
-
C.
hasHistoricPort
chosen
Indicates that an entity possesses or is associated with a port that has historical significance or longstanding historical use.
-
D.
hasPortUse
Indicates that one entity utilizes or is assigned to a particular port for access, communication, or operation.
-
E.
hadPortsAt
Indicates that an entity possessed or maintained ports or harbor facilities at a specified location.
- 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_69f76ee6f1f4819091e2cf9c9e6aee19 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ffe613c03481909f3043ec8bf0bed9 |
completed | May 10, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69ffe4a73fb4819091600725a443981a |
completed | May 10, 2026, 1:51 a.m. |
Created at: May 3, 2026, 4:19 p.m.