Triple
T36172743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cowes–Dinard–St Malo Race |
E1046188
|
entity |
| Predicate | hasStartPort |
P117754
|
FINISHED |
| Object | Cowes Harbour |
—
|
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: Cowes Harbour | Statement: [Cowes–Dinard–St Malo Race, hasStartPort, Cowes Harbour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStartPort Context triple: [Cowes–Dinard–St Malo Race, hasStartPort, Cowes Harbour]
-
A.
typicalStartPort
Indicates the usual or default port number on which a given service, protocol, or application is expected to start or listen.
-
B.
hasPorts
Indicates that an entity is equipped with or provides access points (ports) for connection, communication, or interface with other entities or systems.
-
C.
routeStartPort
chosen
Indicates the port where a route or journey begins.
-
D.
hasPortUse
Indicates that one entity utilizes or is assigned to a particular port for access, communication, or operation.
-
E.
hasUserPort
Indicates that an entity is associated with, exposes, or is accessible through a specific user-facing port or interface.
- 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_69f76e396bc88190b99d221bff9be27a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00315632a8819092290f455babd7ee |
completed | May 10, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_6a002f54a0dc81909b0e54c5e110e67c |
completed | May 10, 2026, 7:10 a.m. |
Created at: May 3, 2026, 4:08 p.m.