Triple
T37245568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Scott |
E923838
|
entity |
| Predicate | militaryConflictParticipated |
P13112
|
FINISHED |
| Object | Battle of Mount Tumbledown |
—
|
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: Battle of Mount Tumbledown | Statement: [Michael Scott, militaryConflictParticipated, Battle of Mount Tumbledown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryConflictParticipated Context triple: [Michael Scott, militaryConflictParticipated, Battle of Mount Tumbledown]
-
A.
warParticipatedIn
chosen
Indicates that an entity took part as a combatant or active participant in a specific war or armed conflict.
-
B.
militaryConflictIn
Indicates that a military conflict takes place within, or is geographically located in, a specified area or region.
-
C.
conflictExperience
Indicates that an entity has undergone or been involved in a conflict, such as a dispute, struggle, or confrontation.
-
D.
militaryConflict
Indicates a relationship where two or more parties are engaged in organized, armed hostilities or warfare against each other.
-
E.
foughtInCountry
Indicates that an entity participated in a fight, battle, or war that took place within the specified country.
- 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_69f76eaabb4c819093b751b139dad551 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
Created at: May 3, 2026, 4:15 p.m.