Triple
T21023253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Deer |
E517869
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Deer burn |
—
|
NE NERFINISHED |
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: Deer burn | Statement: [Old Deer, locatedOn, Deer burn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deer burn Context triple: [Old Deer, locatedOn, Deer burn]
-
A.
Forest Burn
chosen
Forest Burn is a small tributary stream in Northumberland, England, that feeds into the River Coquet.
-
B.
Ezo deer
The Ezo deer is a subspecies of sika deer native to Japan’s northern island of Hokkaido, known for its large size and adaptation to cold, snowy environments.
-
C.
The Wounded Deer
The Wounded Deer is a surreal self-portrait painting by Frida Kahlo that depicts the artist as a stag pierced by arrows, symbolizing her physical pain and emotional suffering.
-
D.
The Wilderness deer park
The Wilderness deer park is a secluded, historic deer enclosure within London's Greenwich Park, known for its naturalistic landscape and resident herd of deer.
-
E.
Elk’s Burn
Elk’s Burn is a small tributary stream that feeds into the River Coquet in Northumberland, England.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5e85d08190a67956a3dbe693de |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 1:55 p.m.