Triple
T24168042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whistling Death |
E599047
|
entity |
| Predicate | sawServiceAfterWar |
P155571
|
FINISHED |
| Object | Korean War (in ground-attack role) |
—
|
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: Korean War (in ground-attack role) | Statement: [Whistling Death, sawServiceAfterWar, Korean War (in ground-attack role)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sawServiceAfterWar Context triple: [Whistling Death, sawServiceAfterWar, Korean War (in ground-attack role)]
-
A.
sawServiceDuring
Indicates that one entity experienced or utilized a service during the time period associated with another entity or event.
-
B.
sawServiceIn
Indicates that an entity observed or experienced a particular service within a specified context, location, or timeframe.
-
C.
sawRevivalIn
Indicates that an entity experienced a renewed interest, resurgence, or comeback during a specified time period or context.
-
D.
sawServicePeriod
Indicates that one entity observed or was aware of the duration or specific period during which a service was provided or active.
-
E.
sawarIndicates
Indicates that one entity carved, engraved, or inscribed another entity (typically text, symbols, or designs) onto a surface or object.
- 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_69e288cbd62881909de32ca64a70c17b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
| PDg | Predicate description generation | batch_69f27a753ca8819095706970d368f762 |
completed | April 29, 2026, 9:39 p.m. |
Created at: April 17, 2026, 11:33 p.m.