Triple
T28218970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runaway Horses |
E711396
|
entity |
| Predicate | followsCharacterAcrossLives |
P66020
|
FINISHED |
| Object | yes |
—
|
LITERAL FINISHED |
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: yes | Statement: [Runaway Horses, followsCharacterAcrossLives, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsCharacterAcrossLives Context triple: [Runaway Horses, followsCharacterAcrossLives, yes]
-
A.
followsCharactersAcross
chosen
Indicates that one entity persistently tracks or accompanies specific characters as they move or act across different scenes, locations, or contexts.
-
B.
followsLifeSpanOfCharacters
Indicates that one entity’s timeline or progression is structured to track or mirror the life spans of specified characters.
-
C.
followsCharacterFrom
Indicates that one character moves or proceeds behind another character, maintaining a trailing or pursuing position relative to them.
-
D.
followsCharactersFrom
Indicates that one entity continues or tracks the narrative, actions, or developments involving specific characters from another entity.
-
E.
followsCharacter
Indicates that one character moves or acts after another character, maintaining a trailing or subsequent position or sequence relative to them.
- 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_69efb51cb5288190818c1f63a266af11 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f760a35b988190904e6267553ad2fe |
completed | May 3, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69f75eb3d6f081908c933474eb359e3d |
completed | May 3, 2026, 2:41 p.m. |
Created at: April 27, 2026, 10:45 p.m.