Triple
T20063859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellis Spear |
E499554
|
entity |
| Predicate | unitRoleAtGettysburg |
P61851
|
FINISHED |
| Object | defense of Little Round Top |
—
|
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: defense of Little Round Top | Statement: [Ellis Spear, unitRoleAtGettysburg, defense of Little Round Top]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitRoleAtGettysburg Context triple: [Ellis Spear, unitRoleAtGettysburg, defense of Little Round Top]
-
A.
roleAtGettysburg
chosen
Indicates the specific role, position, or function an entity held in relation to the Battle of Gettysburg.
-
B.
higherCommanderAtGettysburg
Indicates that one entity served as the superior military commander of another entity during the Battle of Gettysburg.
-
C.
armyCommanderAtGettysburg
Indicates that the person served as an army commander during the Battle of Gettysburg.
-
D.
commanderAtGettysburg
Indicates that the subject served as a military commander at the Battle of Gettysburg.
-
E.
corpsCommanderAtGettysburg
Indicates that the subject served as a corps commander during the Battle of Gettysburg.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66377b6b48190a0a37279f285123e |
completed | April 20, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69e54cee7a5c819084ae4ff26419833f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:39 p.m.