Triple
T22921747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capricious Horses |
E568879
|
entity |
| Predicate | hasLineDescribing |
P150273
|
FINISHED |
| Object | horses rushing toward an abyss |
—
|
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: horses rushing toward an abyss | Statement: [Capricious Horses, hasLineDescribing, horses rushing toward an abyss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLineDescribing Context triple: [Capricious Horses, hasLineDescribing, horses rushing toward an abyss]
-
A.
hasDeFactoLine
Indicates that there exists an unofficial or non-legally recognized boundary or demarcation line functioning in practice between the related entities.
-
B.
hasLineStructure
Indicates that one entity possesses or exhibits a linear arrangement or organization of its components.
-
C.
hasLineSection
Indicates that an entity includes, contains, or is composed of a specific segment or section of a line.
-
D.
hasDominantLines
Indicates that one element in a pair exhibits stronger, more prominent, or controlling linear features relative to the other.
-
E.
hasIconicLine
Indicates that an entity (such as a work or character) is associated with a particularly famous or memorable line of dialogue.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d5658c81908dbbb5882fcc1b8b |
completed | April 29, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69ef3b7c5fc081909ac50c5c8569cc19 |
completed | April 27, 2026, 10:33 a.m. |
| PDg | Predicate description generation | batch_69ef538a115081908982597f79355840 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 17, 2026, 3:43 p.m.