Triple
T1497899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 8th Guards Army |
E29727
|
entity |
| Predicate | awardedTitleFor |
P107
|
FINISHED |
| Object | distinguished service at Stalingrad |
—
|
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: distinguished service at Stalingrad | Statement: [8th Guards Army, awardedTitleFor, distinguished service at Stalingrad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awardedTitleFor Context triple: [8th Guards Army, awardedTitleFor, distinguished service at Stalingrad]
-
A.
awardsTitle
Indicates that an entity confers or grants a specific title or honorific designation to another entity.
-
B.
awardFor
chosen
Indicates that something is given or granted as recognition or a prize for a particular achievement, work, or contribution.
-
C.
confersTitle
Indicates that one entity grants or bestows an official title or designation upon another entity.
-
D.
creditedTitle
Indicates that a particular title or role is formally attributed to an entity as a credit.
-
E.
awardConferred
Indicates that an award or honor has been formally granted by one entity to another.
- 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_69a498dba1d8819093b46a3a8d2485f1 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c6ef5ce88190a6b520525a6d42a3 |
completed | March 1, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69a4c48a8cf48190a6ebf8d44a608a06 |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8:12 p.m.