Triple
T21128774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ajos harbour |
E520627
|
entity |
| Predicate | icebreakingSupport |
P109309
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Ajos harbour, icebreakingSupport, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: icebreakingSupport Context triple: [Ajos harbour, icebreakingSupport, yes]
-
A.
icebreakingCapability
chosen
Indicates the ability of a vessel or system to break through ice-covered waters to enable or maintain navigation.
-
B.
iceBreakupIn
Indicates that the breakup or disintegration of ice occurs within or at a specified location or region.
-
C.
helpsBreakInto
Indicates that one entity assists another in gaining unauthorized access to a place, system, or object.
-
D.
helpsIn
Indicates that one entity provides assistance, support, or aid to another entity in performing or achieving a particular task, activity, or goal.
-
E.
openingEngagementOf
Indicates that one event, action, or interaction serves as the initial or first engagement within a larger sequence, context, or relationship involving another entity or event.
- 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_69e0b50b53048190ae34e8abbe3c5ada |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7223b4c4c8190b9fffa610588651e |
completed | April 21, 2026, 7:07 a.m. |
| PD | Predicate disambiguation | batch_69e5f5ed6c8c8190b31092a5d4c3de5d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 2:56 p.m.