Triple
T21977049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shiloh Church |
E542731
|
entity |
| Predicate | battlefieldFeature |
P61840
|
FINISHED |
| Object | center of early Confederate attack sector |
—
|
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: center of early Confederate attack sector | Statement: [Shiloh Church, battlefieldFeature, center of early Confederate attack sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battlefieldFeature Context triple: [Shiloh Church, battlefieldFeature, center of early Confederate attack sector]
-
A.
battlefieldFunction
Indicates the role or purpose an entity serves within a combat or battlefield context, such as its tactical or operational function during warfare.
-
B.
featuresBattle
Indicates that one entity includes, presents, or involves a battle as a significant element or event.
-
C.
battleCharacteristic
Indicates a relationship where a specific trait, quality, or feature is attributed to a battle or combat scenario.
-
D.
battlefieldSector
chosen
Indicates a specific area or zone of a battlefield in which a military unit, action, or event is located or occurs.
-
E.
battlefieldOf
Indicates that a location is the site where a particular battle or military engagement took place.
- F. None of above.
Provenance (3 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12489889c81909c847cf2f6808d85 |
completed | April 28, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:03 p.m.