Triple
T28890821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oathbreakers of the Paths of the Dead |
E732687
|
entity |
| Predicate | aidedInBattleOf |
P60437
|
FINISHED |
| Object | Pelargir |
—
|
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: Pelargir | Statement: [Oathbreakers of the Paths of the Dead, aidedInBattleOf, Pelargir]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aidedInBattleOf Context triple: [Oathbreakers of the Paths of the Dead, aidedInBattleOf, Pelargir]
-
A.
battleWasPartOf
Indicates that a specific battle occurred as a component or phase within a larger military campaign, war, or conflict.
-
B.
refersToPersonNotableBattle
Indicates that a person is associated with or identified by a specific notable battle in which they played a significant role.
-
C.
battledIn
Indicates that two or more entities engaged in a battle or conflict that took place at a specific location or during a particular event.
-
D.
laterFoughtAlongside
chosen
Indicates that two entities, who were previously in some other relationship or context, subsequently fought on the same side as allies in a conflict or battle.
-
E.
battleParticipated
Indicates that an entity took part in a specific battle as a combatant or participant.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65a75dfc88190b919126bcafd64c7 |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f6576487e081908d802f1caf59c423 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 7:55 a.m.