Triple
T23235978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gerard Lake |
E581293
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Elizabeth Lake |
—
|
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: Elizabeth Lake | Statement: [Gerard Lake, child, Elizabeth Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Lake Context triple: [Gerard Lake, child, Elizabeth Lake]
-
A.
Elizabeth Lake
Elizabeth Lake is a residential and recreational inland lake located in Waterford Township in Oakland County, Michigan.
-
B.
Radley Lake
Radley Lake is a scenic body of water in Oxfordshire, England, closely associated with and forming part of the grounds of Radley College.
-
C.
Carrie Lake
Carrie Lake was the wife of Joy Morton, the American businessman and founder of the Morton Salt Company.
-
D.
Last Mountain Lake
Last Mountain Lake is a long, narrow glacial lake in southern Saskatchewan, Canada, known for its important bird sanctuary and recreational activities.
-
E.
Croton Lake
Croton Lake is a reservoir in Westchester County, New York, that serves as a key component of New York City’s drinking water supply system.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192e98dec8190a23385600bed9ae0 |
completed | April 29, 2026, 5:11 a.m. |
Created at: April 17, 2026, 4:09 p.m.