Triple
T36732532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Via Egnatia trade network |
E907377
|
entity |
| Predicate | linkedMaritimePort |
P115895
|
FINISHED |
| Object | Neapolis (Kavala) |
—
|
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: Neapolis (Kavala) | Statement: [Via Egnatia trade network, linkedMaritimePort, Neapolis (Kavala)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedMaritimePort Context triple: [Via Egnatia trade network, linkedMaritimePort, Neapolis (Kavala)]
-
A.
linkedToInlandPort
Indicates a relationship where something has a direct connection or association with an inland port, such as for transport, logistics, or access purposes.
-
B.
maritimeGatewayFor
Indicates a relationship where one location serves as the primary seaport or ocean-access point enabling maritime connectivity and trade for another location.
-
C.
associatedHarbour
chosen
Indicates a relationship where a place, route, or maritime entity is linked to or served by a particular harbour.
-
D.
isPortOf
Indicates that one location or facility serves as a port or harbor for another place, entity, or transportation route.
-
E.
permanentPortFacilities
Indicates that an entity has fixed, long-term port infrastructure used for maritime operations, such as docks, piers, or terminals that are not temporary or mobile.
- 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fec4cffed08190b5e5e7cc0c87493e |
completed | May 9, 2026, 5:23 a.m. |
| PD | Predicate disambiguation | batch_69fec2ea7fe08190bd751b39515f69d1 |
completed | May 9, 2026, 5:15 a.m. |
Created at: May 3, 2026, 4:12 p.m.