Triple
T91431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croton River |
E1836
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
China Brook
China Brook is a small tributary stream associated with New York’s Croton River watershed.
|
E15368
|
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: China Brook | Statement: [Croton River, hasPart, China Brook]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: China Brook Context triple: [Croton River, hasPart, China Brook]
-
A.
Walkill River
The Walkill River is a north-flowing river in New Jersey and New York that drains part of the Appalachian Valley before joining the Hudson River.
-
B.
Kaw
The Kaw, also known as the Kansa, are a Native American tribe originally from the central Midwestern United States, particularly the region that is now Kansas.
-
C.
Choapa River
The Choapa River is a significant watercourse in north-central Chile that flows through the Coquimbo Region toward the Pacific Ocean, supporting local agriculture and settlements along its basin.
-
D.
Yangtze River
The Yangtze River is the longest river in Asia and a crucial waterway in China, supporting major cities, transportation, agriculture, and hydroelectric power.
-
E.
Esopus Creek
Esopus Creek is a scenic stream in New York’s Catskill Mountains known for trout fishing, recreation, and its role in the New York City water supply system.
- 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: China Brook Triple: [Croton River, hasPart, China Brook]
Generated description
China Brook is a small tributary stream associated with New York’s Croton River watershed.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: China Brook Target entity description: China Brook is a small tributary stream associated with New York’s Croton River watershed.
-
A.
Walkill River
The Walkill River is a north-flowing river in New Jersey and New York that drains part of the Appalachian Valley before joining the Hudson River.
-
B.
Kaw
The Kaw, also known as the Kansa, are a Native American tribe originally from the central Midwestern United States, particularly the region that is now Kansas.
-
C.
Choapa River
The Choapa River is a significant watercourse in north-central Chile that flows through the Coquimbo Region toward the Pacific Ocean, supporting local agriculture and settlements along its basin.
-
D.
Yangtze River
The Yangtze River is the longest river in Asia and a crucial waterway in China, supporting major cities, transportation, agriculture, and hydroelectric power.
-
E.
Esopus Creek
Esopus Creek is a scenic stream in New York’s Catskill Mountains known for trout fishing, recreation, and its role in the New York City water supply 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a24f6c29888190890caa7872d63ac6 |
completed | Feb. 28, 2026, 2:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2aa42201881909b236a42e982a696 |
completed | Feb. 28, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_69a2abf742d081909f8d79aaacb6b7f8 |
completed | Feb. 28, 2026, 8:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a2ac6f577081909dced4081ddb8bcb |
completed | Feb. 28, 2026, 8:50 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.