Triple
T4876259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flag of South Georgia and the South Sandwich Islands |
E109211
|
entity |
| Predicate | usesOn |
P2367
|
FINISHED |
| Object | land |
—
|
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: land | Statement: [Flag of South Georgia and the South Sandwich Islands, usesOn, land]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesOn Context triple: [Flag of South Georgia and the South Sandwich Islands, usesOn, land]
-
A.
usedOn
chosen
Indicates that one entity is applied to, operated on, or otherwise utilized in relation to another entity.
-
B.
usedOnMode
Indicates that something is applied, operated, or functions specifically in a given mode or operational setting.
-
C.
usedOnFront
Indicates that something is applied, displayed, or positioned on the front side or front-facing part of another object or entity.
-
D.
usedWith
Indicates that one entity is typically or appropriately employed together with another entity in a combined or complementary use.
-
E.
endsOn
Indicates that one entity terminates or concludes precisely at the boundary or endpoint of another entity.
- 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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c28e56081908ee411ac94c3769e |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.