Triple
T14465534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Dormeur du val |
E358697
|
entity |
| Predicate | hasEndingImage |
P68797
|
FINISHED |
| Object | two red holes in the soldier's side |
—
|
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: two red holes in the soldier's side | Statement: [Le Dormeur du val, hasEndingImage, two red holes in the soldier's side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndingImage Context triple: [Le Dormeur du val, hasEndingImage, two red holes in the soldier's side]
-
A.
hasEnding
Indicates that one entity concludes with, or terminates in, another entity (such as a specific substring, segment, or final component).
-
B.
hasEnd
Indicates that one entity serves as the terminal point, boundary, or conclusion of another entity or process.
-
C.
hasUnfinishedEnding
Indicates that an entity concludes in an incomplete, unresolved, or open-ended manner rather than reaching a fully finished state.
-
D.
containsImage
chosen
Indicates that one entity includes or embeds an image as part of its content or structure.
-
E.
hasLandmarkAtEnd
Indicates that a landmark is located at the terminal point or end of a specified path, route, or boundary.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91f6d4c08190a12e9a5901ee3508 |
completed | April 14, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69de5c42bd3c81909a62acf30cc24d1e |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:19 a.m.