Triple
T26988259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Militia against the Saviors |
E679789
|
entity |
| Predicate | unitesCharacter |
P35330
|
FINISHED |
| Object | King Ezekiel |
—
|
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: King Ezekiel | Statement: [Militia against the Saviors, unitesCharacter, King Ezekiel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitesCharacter Context triple: [Militia against the Saviors, unitesCharacter, King Ezekiel]
-
A.
unites
chosen
Indicates that one entity brings together multiple entities into a single, cohesive whole or shared state.
-
B.
unionForces
Indicates that multiple forces are combined into a single, unified force acting together.
-
C.
unitedWithTitle
Indicates that an entity has been joined or merged with another entity under a shared or combined title.
-
D.
allyOfCharacter
Indicates that one character maintains an alliance or supportive partnership with another character.
-
E.
usesCharactersAs
Indicates that one entity employs or incorporates specific characters (such as letters, symbols, or glyphs) from another entity for its representation or functioning.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f621cbc48881908d104c648c91c715 |
completed | May 2, 2026, 4:09 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 6:50 a.m.