Triple
T5960531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Letters from Iwo Jima |
E132624
|
entity |
| Predicate | followsPerspective |
P8789
|
FINISHED |
| Object | Japanese 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: Japanese soldiers | Statement: [Letters from Iwo Jima, followsPerspective, Japanese soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsPerspective Context triple: [Letters from Iwo Jima, followsPerspective, Japanese soldiers]
-
A.
perspectiveOf
chosen
Indicates that something is expressed, depicted, or understood from the viewpoint or standpoint of a particular entity.
-
B.
followsFace
Indicates that one entity adjusts its position or orientation to continuously track and remain aligned with another entity’s face.
-
C.
followsBy
Indicates that one event, state, or entity occurs or comes immediately after another in a sequence or order.
-
D.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
E.
useOfPerspective
Indicates that one entity adopts or applies a particular visual, narrative, or conceptual viewpoint in relation to another entity or context.
- 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_69c0086c2364819091e9fe2f58fa2517 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c03fb7f8a88190a8bd45208bda4a03 |
completed | March 22, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69c0335a635881909c58c1ef0f97f1e8 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 4:02 p.m.