Triple
T20600053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clinton River |
E506151
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object |
Red Run
Red Run is a smaller stream in Michigan that feeds into the Clinton River as part of its watershed system.
|
E1440063
|
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: Red Run | Statement: [Clinton River, hasTributary, Red Run]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Red Run Context triple: [Clinton River, hasTributary, Red Run]
-
A.
Roaring Run
Roaring Run is a stream in western Pennsylvania known for its scenic gorge, hiking trails, and role as a tributary feeding into the Kiskiminetas River.
-
B.
Deep Run
Deep Run is a stream in central Maryland that serves as a tributary of the Little Patuxent River within the Chesapeake Bay watershed.
-
C.
Deep Run
Deep Run is a significant tributary stream feeding into Maryland’s Patapsco River, contributing to its watershed and regional drainage system.
-
D.
The Runners
The Runners are an American record production duo known for crafting polished, radio-friendly hip hop and R&B tracks for major artists.
-
E.
Redbud Run
Redbud Run is a small stream in the Opequon Creek watershed of the Shenandoah Valley, contributing to the Potomac River basin in the eastern United States.
- 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: Red Run Triple: [Clinton River, hasTributary, Red Run]
Generated description
Red Run is a smaller stream in Michigan that feeds into the Clinton River as part of its watershed system.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Red Run Target entity description: Red Run is a smaller stream in Michigan that feeds into the Clinton River as part of its watershed system.
-
A.
Roaring Run
Roaring Run is a stream in western Pennsylvania known for its scenic gorge, hiking trails, and role as a tributary feeding into the Kiskiminetas River.
-
B.
Deep Run
Deep Run is a stream in central Maryland that serves as a tributary of the Little Patuxent River within the Chesapeake Bay watershed.
-
C.
Deep Run
Deep Run is a significant tributary stream feeding into Maryland’s Patapsco River, contributing to its watershed and regional drainage system.
-
D.
The Runners
The Runners are an American record production duo known for crafting polished, radio-friendly hip hop and R&B tracks for major artists.
-
E.
Redbud Run
Redbud Run is a small stream in the Opequon Creek watershed of the Shenandoah Valley, contributing to the Potomac River basin in the eastern United States.
- 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_69e0b4ba6ae88190af871e1f9522c704 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aa1ef9ac8190b05e23c149529cb9 |
completed | April 20, 2026, 10:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08b3f11f088190b384b6d283ca3ffc |
completed | May 16, 2026, 6:14 p.m. |
| NEDg | Description generation | batch_6a08b58a598c819096740660d6e3c036 |
completed | May 16, 2026, 6:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08b62bc9b88190b3772f11c8335741 |
completed | May 16, 2026, 6:23 p.m. |
Created at: April 16, 2026, 11:41 a.m.