Triple
T18623494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maspeth |
E455214
|
entity |
| Predicate | nearWaterBody |
P8567
|
FINISHED |
| Object | English Kills |
—
|
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: English Kills | Statement: [Maspeth, nearWaterBody, English Kills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: English Kills Context triple: [Maspeth, nearWaterBody, English Kills]
-
A.
English Kills
chosen
English Kills is a tributary and industrial waterway in Brooklyn, New York City, forming part of the Newtown Creek system.
-
B.
The English Way of Death
The English Way of Death is a Doctor Who novel by Gareth Roberts, known for its witty, pastiche-rich take on the Fourth Doctor and Romana II in a 1930s-set adventure.
-
C.
Brance Macabre
Brance Macabre is a music producer known for his work on the hip-hop album "The Weatherman LP."
-
D.
A Few Dying Words
"A Few Dying Words" is a crime novel by Paula Gosling, known for its suspenseful plotting and character-driven mystery.
-
E.
The Murder
"The Murder" is the iconic, shrieking string cue composed by Bernard Herrmann for Alfred Hitchcock’s Psycho, most famously underscoring the film’s shower scene.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f02dc248190a82341eeb2473593 |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.