Triple
T12137783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lower Largo |
E289105
|
entity |
| Predicate | hasNeighbour |
P5707
|
FINISHED |
| Object | Upper Largo |
E285828
|
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: Upper Largo | Statement: [Lower Largo, hasNeighbour, Upper Largo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upper Largo Context triple: [Lower Largo, hasNeighbour, Upper Largo]
-
A.
Upper Largo
chosen
Upper Largo is a small village in Fife, Scotland, situated near the southern coast by Largo Bay.
-
B.
Lower Largo
Lower Largo is a small coastal village in Fife, Scotland, known as the birthplace of Alexander Selkirk, the sailor who inspired Daniel Defoe’s Robinson Crusoe.
-
C.
Largo
Largo is a suburban community in Prince George’s County, Maryland, located just east of Washington, D.C.
-
D.
Largo
Largo is a genre-blending jazz album by pianist Brad Mehldau that incorporates rock, electronic, and orchestral elements into his distinctive improvisational style.
-
E.
Riverchase
Riverchase is a major commercial and retail area in Hoover, Alabama, best known for its large shopping centers and surrounding businesses.
- 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_69d6ab4b5e4c81909950b17151eb0951 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9158dd00c819082651891898b91bb |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a7baee88190a32a5a3cd0b8a326 |
completed | May 2, 2026, 2:30 p.m. |
Created at: April 8, 2026, 9:49 p.m.