Triple
T34179652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Chattanooga |
E876776
|
entity |
| Predicate | hookerRole |
P178486
|
FINISHED |
| Object | Joseph Hooker attacked Lookout Mountain |
—
|
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: Joseph Hooker attacked Lookout Mountain | Statement: [Battle of Chattanooga, hookerRole, Joseph Hooker attacked Lookout Mountain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hookerRole Context triple: [Battle of Chattanooga, hookerRole, Joseph Hooker attacked Lookout Mountain]
-
A.
HodRole
Indicates that an entity holds the role or position of Head of Department (HOD) in relation to a specified department or organizational unit.
-
B.
hogonRole
Indicates that an entity holds or is assigned the role or office of a hogon (a specific traditional or religious leadership position).
-
C.
HarrisonRole
Indicates that an entity holds, has held, or is associated with a specific role or position in relation to Harrison.
-
D.
roleInWatchmen
Indicates that one entity has a specific role or function within the context of the work "Watchmen" in relation to the other entity.
-
E.
catchingRole
Indicates the role an entity plays in the act of catching something or someone within an interaction or event.
- 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_69f349ae640c8190b9cd220b5368d8b6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f710aaff588190adc6cc5b7d5424cc |
completed | May 3, 2026, 9:08 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
| PDg | Predicate description generation | batch_69f70fddd43c819088dee5a448c72cbe |
completed | May 3, 2026, 9:05 a.m. |
Created at: May 1, 2026, 1:54 a.m.