Triple
T27017791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Rocky Mount |
E680581
|
entity |
| Predicate | notableCommanderLoyalist |
P200019
|
FINISHED |
| Object | George Turnbull |
—
|
NE NERFINISHED |
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: George Turnbull | Statement: [Battle of Rocky Mount, notableCommanderLoyalist, George Turnbull]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCommanderLoyalist Context triple: [Battle of Rocky Mount, notableCommanderLoyalist, George Turnbull]
-
A.
notableCommanderOf
Indicates that an individual is a distinguished or historically significant commander associated with leading a particular military unit, force, or organization.
-
B.
notableCommanderOrAlly
Indicates that an entity is a significant military leader or important ally associated with another entity, such as a person, group, or organization.
-
C.
notableCommanderSide
Indicates that a particular military or strategic side is notably commanded or led by a specified commander.
-
D.
notableCommanderNationality
Indicates that the notable commander associated with an entity has the specified nationality.
-
E.
notableCommanderAmerican
Indicates that the subject served as a notable military commander who is American.
- 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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69ff6c061c6c81909ff485e9cafc88a2 |
completed | May 9, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ff6aaf886c8190a3c87d089453f3de |
completed | May 9, 2026, 5:11 p.m. |
| PDg | Predicate description generation | batch_69ff6c04fa208190b1fab40a71ef923f |
completed | May 9, 2026, 5:16 p.m. |
Created at: April 27, 2026, 7:07 a.m.