Triple
T11692423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commercial Resupply Services 1 |
E277900
|
entity |
| Predicate | capsuleBerthingPort |
P14974
|
FINISHED |
| Object | Harmony nadir port |
—
|
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: Harmony nadir port | Statement: [Commercial Resupply Services 1, capsuleBerthingPort, Harmony nadir port]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capsuleBerthingPort Context triple: [Commercial Resupply Services 1, capsuleBerthingPort, Harmony nadir port]
-
A.
berthingSystem
Indicates a system or mechanism used to dock, moor, or secure one vehicle, vessel, or structure to another.
-
B.
berthingOrDockingTarget
chosen
Indicates that an entity serves as the location or structure where a vessel or vehicle is intended to berth or dock.
-
C.
berthType
Indicates the specific kind or category of berth associated with an entity, such as the type of sleeping or docking space provided.
-
D.
mooredAt
Indicates that one object, typically a vessel or floating structure, is secured or anchored at a specific location or facility.
-
E.
harbourName
Indicates the name assigned to a harbour in which an entity is located or associated.
- 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_69d6aafe02d881909900d54ad7d4af84 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a47a3ddc819098e208611148d15b |
completed | April 10, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69d88a7b30948190b616a9db5c5488d5 |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:40 p.m.