Triple
T28205222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German Army (in War Horse) |
E716997
|
entity |
| Predicate | portrayedThrough |
P37849
|
FINISHED |
| Object | various unnamed German soldiers |
—
|
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: various unnamed German soldiers | Statement: [German Army (in War Horse), portrayedThrough, various unnamed German soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedThrough Context triple: [German Army (in War Horse), portrayedThrough, various unnamed German soldiers]
-
A.
portrayedVia
chosen
Indicates that one entity is represented, depicted, or expressed through a particular medium, method, or channel.
-
B.
portrayedAsFrom
Indicates that one entity is depicted or represented as originating from, or belonging to, the place or source specified by another entity.
-
C.
portraysPersonAs
Indicates that one entity represents, depicts, or characterizes another person in a particular way or role.
-
D.
portrayalFeature
Indicates that one entity serves as a characteristic, aspect, or attribute highlighted in the depiction or representation of another entity.
-
E.
portrayalLedTo
Indicates that one entity’s portrayal of another caused or significantly contributed to a subsequent outcome, reaction, or state involving that other entity.
- 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_69efd6b826908190857e6e7dad74ed93 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 27, 2026, 10:35 p.m.