Triple
T13982849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green-Wood Cemetery |
E336357
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Sunset Park, Brooklyn |
E35726
|
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: Sunset Park, Brooklyn | Statement: [Green-Wood Cemetery, locatedNear, Sunset Park, Brooklyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunset Park, Brooklyn Context triple: [Green-Wood Cemetery, locatedNear, Sunset Park, Brooklyn]
-
A.
Sunset Park
Sunset Park is a public recreational park located in Mauldin, South Carolina.
-
B.
Sunset Park
Sunset Park is a public recreational park located in Storm Lake, Iowa.
-
C.
Sunset Park
Sunset Park is a public recreational park in Sturgeon Bay, Wisconsin, known for its waterfront views and outdoor amenities.
-
D.
Sunset Park
chosen
Sunset Park is a diverse, largely working-class neighborhood in southwestern Brooklyn known for its namesake hilltop park with sweeping views of New York Harbor and the Manhattan skyline.
-
E.
Sunset Park
"Sunset Park" is a 2010 novel by American author Paul Auster that follows a group of young squatters in a foreclosed house in Brooklyn as they grapple with economic hardship, fractured families, and the search for meaning.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ea2e8808190a1203a6386224bd8 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac9231888190ad8cb460db73bdb4 |
completed | May 6, 2026, 9:03 p.m. |
Created at: April 9, 2026, 10:18 p.m.