Triple
T26493811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turner’s Gap |
E669225
|
entity |
| Predicate | distanceToAntietam |
P196690
|
FINISHED |
| Object | approximately 10 miles east of Antietam battlefield |
—
|
LITERAL FINISHED |
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: approximately 10 miles east of Antietam battlefield | Statement: [Turner’s Gap, distanceToAntietam, approximately 10 miles east of Antietam battlefield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToAntietam Context triple: [Turner’s Gap, distanceToAntietam, approximately 10 miles east of Antietam battlefield]
-
A.
distanceFromGettysburg
Indicates the spatial distance between a given entity or location and Gettysburg.
-
B.
distanceToBaltimoreInMiles
Indicates the numerical distance, measured in miles, between a given location and the city of Baltimore.
-
C.
distanceToAnnapolisMiles
Indicates the physical distance, measured in miles, between a given location and Annapolis.
-
D.
distanceFromFord’sTheatre
Indicates the spatial distance between an entity and Ford’s Theatre.
-
E.
distanceFromJamestown
Indicates the measured distance between a given location and Jamestown.
- F. None of above. chosen
Provenance (4 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_69eeb319007081909642b414b114b35a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69fe629b4fa481908467c7c41b77f0c6 |
completed | May 8, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69fe61bb260c819083f9378a3a06ca47 |
completed | May 8, 2026, 10:20 p.m. |
| PDg | Predicate description generation | batch_69fe629a8d4c8190b4aa4dee39efc0a6 |
completed | May 8, 2026, 10:24 p.m. |
Created at: April 27, 2026, 1:06 a.m.