Triple
T16308703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Battle That Saved Washington |
E395989
|
entity |
| Predicate | belligerent |
P375
|
FINISHED |
| Object |
Union
The Union was the federal government and Northern states of the United States that fought to preserve the nation and end slavery during the American Civil War.
|
E22849
|
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: Union | Statement: [The Battle That Saved Washington, belligerent, Union]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Union Context triple: [The Battle That Saved Washington, belligerent, Union]
-
A.
Union
Union is the commonly used short name for the Major League Soccer club Philadelphia Union.
-
B.
Union
"Union" is a song featured on the album "Monkey Business" by the Black Eyed Peas.
-
C.
Union
Union is a town in Broome County, New York, that forms part of the Binghamton metropolitan area.
-
D.
Union
Union is a major transit hub in downtown Toronto that serves as the city's primary subway and railway station complex.
-
E.
Union
The Union refers to the central (federal) government of India, which holds nationwide legislative and executive authority distinct from state governments.
- 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: Union Triple: [The Battle That Saved Washington, belligerent, Union]
Generated description
The Union was the federal government and Northern states of the United States that fought to preserve the nation and end slavery during the American Civil War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Union Target entity description: The Union was the federal government and Northern states of the United States that fought to preserve the nation and end slavery during the American Civil War.
-
A.
Union
chosen
The Union was the federal government and Northern states of the United States that opposed the seceding Confederate states during the American Civil War.
-
B.
Union
The Union refers to the central (federal) government of India, which holds nationwide legislative and executive authority distinct from state governments.
-
C.
Union
Union was a small community in the Town of Neversink, New York, that was permanently abandoned and flooded during the creation of New York City’s upstate reservoir system.
-
D.
Union
Union is a 1991 progressive rock album by the combined lineups of Yes and Anderson Bruford Wakeman Howe, notable for uniting multiple eras of the band’s members on one record.
-
E.
Union
Union is a town in Broome County, New York, that forms part of the Binghamton metropolitan area.
- F. None of above.
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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288d776808190a7c9918477f07216 |
completed | April 17, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001fa517908190a29caa0156b1d1cd |
completed | May 10, 2026, 6:03 a.m. |
| NEDg | Description generation | batch_6a00204bc3dc8190af075707f8989e3a |
completed | May 10, 2026, 6:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00215cc7a48190a5c4219d15749aa2 |
completed | May 10, 2026, 6:10 a.m. |
Created at: April 10, 2026, 5:06 a.m.