Triple
T31686205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RRS Bransfield |
E808667
|
entity |
| Predicate | supportedStation |
P65507
|
FINISHED |
| Object | Rothera Research Station |
E71323
|
NE 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: Rothera Research Station | Statement: [RRS Bransfield, supportedStation, Rothera Research Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedStation Context triple: [RRS Bransfield, supportedStation, Rothera Research Station]
-
A.
ownedStation
Indicates that one entity possesses ownership or control over a particular station.
-
B.
supportedIn
Indicates that one entity is valid, applicable, or functionally enabled within the context, environment, platform, or scope defined by another entity.
-
C.
supportedEquipment
Indicates that one entity provides compatibility with, or operational support for, a specified piece of equipment.
-
D.
associatedStation
chosen
Indicates a relationship where one entity is linked or connected to a particular station as its relevant or related station.
-
E.
supportsStationMode
Indicates that one entity provides or enables a “station mode” capability or operation for another entity.
- F. None of above.
Provenance (4 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b84bf9ca08190b60c32846af2f23e |
completed | June 12, 2026, 4:02 a.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 30, 2026, 11:06 p.m.