Triple
T37907845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holland America Line |
E945602
|
entity |
| Predicate | flagshipPort |
P51783
|
FINISHED |
| Object | Port of Rotterdam (historical) |
—
|
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: Port of Rotterdam (historical) | Statement: [Holland America Line, flagshipPort, Port of Rotterdam (historical)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flagshipPort Context triple: [Holland America Line, flagshipPort, Port of Rotterdam (historical)]
-
A.
flagshipRouteOf
Indicates that a particular route is the primary, most important, or most representative route operated by a given carrier or organization.
-
B.
flagshipCity
Indicates that a city serves as the primary, most representative, or leading example within a larger group, organization, or context.
-
C.
isPortOf
Indicates that one location or facility serves as a port or harbor for another place, entity, or transportation route.
-
D.
isPortOfCallFor
Indicates that a location serves as a scheduled stop or destination for a ship, vehicle, or journey.
-
E.
isHomePortOf
chosen
Indicates that a particular location serves as the primary base or port where a vessel or fleet is officially registered, stationed, or regularly returns.
- 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_69f76ef20bb0819088b5b6ceecb0b8fc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69fbbd166a488190b1bf9316b0790801 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.