Triple
T13586915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duns |
E324589
|
entity |
| Predicate | isNear |
P350
|
FINISHED |
| Object | Greenlaw |
E324590
|
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: Greenlaw | Statement: [Duns, isNear, Greenlaw]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greenlaw Context triple: [Duns, isNear, Greenlaw]
-
A.
Greenlaw
chosen
Greenlaw is a small historic town in the Scottish Borders that once served as the county town of Berwickshire.
-
B.
Palmore
Palmore is a surname that functions as a variant form of the more common family name Palmer.
-
C.
Langdell
Langdell is a surname most notably associated with Christopher Columbus Langdell, the influential 19th-century dean of Harvard Law School who pioneered the case method of legal education.
-
D.
Goodwin
Goodwin is the surname of American actress Ginnifer Goodwin, known for her roles in "Once Upon a Time" and "Big Love."
-
E.
Goodwin
Goodwin is a masculine given name most notably borne by Goodwin Knight, who served as the 31st governor of California in the mid-20th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d80769100c819099111274614f5ed2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb054c6008190839384ce26e8f71a |
completed | April 12, 2026, 2:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76bc148d08190821614a866d1a7f0 |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:49 p.m.