Triple
T421620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rondout Creek |
E8114
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object |
Beer Kill
Beer Kill is a small stream in New York’s Hudson Valley that serves as a tributary within the Rondout Creek watershed.
|
E53355
|
NE FINISHED |
How this triple was built (4 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: Beer Kill | Statement: [Rondout Creek, hasTributary, Beer Kill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beer Kill Context triple: [Rondout Creek, hasTributary, Beer Kill]
-
A.
Kill Van Kull
Kill Van Kull is a tidal strait in New York Harbor that serves as a major shipping channel between Newark Bay and the Upper New York Bay.
-
B.
Blacker
Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
-
C.
Stumptown
Stumptown is a historic nickname for Portland, Oregon, referencing the city’s rapid 19th-century growth that left tree stumps scattered throughout the area.
-
D.
Las Bombas
Las Bombas is a Metrobús station in Mexico City that serves as a terminus on Line 5 of the bus rapid transit system.
-
E.
Mystic Massacre
Mystic Massacre was a pivotal and brutal 1637 attack during the Pequot War in which English colonists and their Native allies destroyed a fortified Pequot village, killing hundreds and effectively breaking Pequot resistance in New England.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Beer Kill Triple: [Rondout Creek, hasTributary, Beer Kill]
Generated description
Beer Kill is a small stream in New York’s Hudson Valley that serves as a tributary within the Rondout Creek watershed.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Beer Kill Target entity description: Beer Kill is a small stream in New York’s Hudson Valley that serves as a tributary within the Rondout Creek watershed.
-
A.
Kill Van Kull
Kill Van Kull is a tidal strait in New York Harbor that serves as a major shipping channel between Newark Bay and the Upper New York Bay.
-
B.
Blacker
Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
-
C.
Silver Taps
Silver Taps is a solemn Texas A&M University tradition honoring deceased students with a nighttime campus ceremony featuring a bugle call and silent remembrance.
-
D.
Stumptown
Stumptown is a historic nickname for Portland, Oregon, referencing the city’s rapid 19th-century growth that left tree stumps scattered throughout the area.
-
E.
Las Bombas
Las Bombas is a Metrobús station in Mexico City that serves as a terminus on Line 5 of the bus rapid transit system.
- F. None of above. chosen
Provenance (5 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_69a2e7f1d1bc81909cf2dc9754a3c334 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eec0e9dc81908c08b209ce5278ef |
completed | Feb. 28, 2026, 1:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a425453ee08190bbed80bd65729e51 |
completed | March 1, 2026, 11:38 a.m. |
| NEDg | Description generation | batch_69a42635b4388190a69f63491b88c466 |
completed | March 1, 2026, 11:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4268e6a5081909660c486d53db99e |
completed | March 1, 2026, 11:44 a.m. |
Created at: Feb. 28, 2026, 1:11 p.m.