Triple
T23941371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Royal Harbour |
E602789
|
entity |
| Predicate | harbourFor |
P12053
|
FINISHED |
| Object | commercial vessels |
—
|
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: commercial vessels | Statement: [Princess Royal Harbour, harbourFor, commercial vessels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: harbourFor Context triple: [Princess Royal Harbour, harbourFor, commercial vessels]
-
A.
harbourUse
chosen
Indicates how a harbour is used or purposed, such as for specific activities, functions, or types of maritime operations.
-
B.
harbourSystem
Indicates a relationship where one entity serves as a harbor or port system that accommodates, services, or supports another entity (such as ships, goods, or maritime operations).
-
C.
harbourSide
Indicates a location or object that is situated alongside or directly adjacent to a harbour.
-
D.
harbor
Indicates providing shelter, protection, or refuge for someone or something, often by keeping them in a safe or hidden place.
-
E.
harbourAlsoKnownAs
Indicates that a harbour is referred to by an alternative name or alias.
- 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d02a1b308190a2d101774b455417 |
completed | April 29, 2026, 9:32 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:09 p.m.