Triple
T9941496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saco Bay |
E194092
|
entity |
| Predicate | hasBeach |
P1922
|
FINISHED |
| Object | Ferry Beach |
E611877
|
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: Ferry Beach | Statement: [Saco Bay, hasBeach, Ferry Beach]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ferry Beach Context triple: [Saco Bay, hasBeach, Ferry Beach]
-
A.
Ferry Beach
chosen
Ferry Beach is a coastal recreational beach area in Saco, Maine, known for its sandy shoreline and access to the Atlantic Ocean.
-
B.
Iracema Beach
Iracema Beach is a popular urban beach and nightlife hub in Fortaleza, Brazil, known for its lively boardwalk, bars, and cultural events.
-
C.
Stonehaven Beach
Stonehaven Beach is a scenic sandy shoreline on Scotland’s northeast coast, known for its picturesque harbor views and proximity to the historic Dunnottar Castle.
-
D.
Filey Beach
Filey Beach is a long, sandy seaside beach on the North Yorkshire coast of England, known for its gently sloping shore, family-friendly atmosphere, and traditional British resort charm.
-
E.
Cowell Beach
Cowell Beach is a popular sandy beach and surf spot located along the Santa Cruz waterfront near the Santa Cruz Beach Boardwalk in California.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb610905c81909d669265c92021a5 |
completed | April 2, 2026, 12:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d281d5f6188190a7e657b1bd9bc607 |
completed | April 5, 2026, 3:37 p.m. |
Created at: March 30, 2026, 8:44 p.m.