Triple
T32307721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle "E" |
E825411
|
entity |
| Predicate | hasSubAwards |
P51490
|
FINISHED |
| Object | departmental efficiency awards |
—
|
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: departmental efficiency awards | Statement: [Battle "E", hasSubAwards, departmental efficiency awards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubAwards Context triple: [Battle "E", hasSubAwards, departmental efficiency awards]
-
A.
hasSubsequentAward
Indicates that an entity has received an additional award that follows a previous award in time or sequence.
-
B.
hasSeparateAwardFor
chosen
Indicates that there exists a distinct, dedicated award specifically recognizing the related entity, separate from other general or combined awards.
-
C.
hasAwarded
Indicates that one entity has given or conferred an award to another entity.
-
D.
hasRelativeWithAward
Indicates that one entity has a relative who has received an award.
-
E.
hasAwardConnection
Indicates a relationship where an entity is connected to an award, such as by receiving, being nominated for, or otherwise associated with that award.
- 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_69f3491213b88190a57094d8697a7455 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fefa064ab48190925759950d0d94d9 |
completed | May 9, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69fef96ae5d08190b027435753c44821 |
completed | May 9, 2026, 9:07 a.m. |
Created at: May 1, 2026, 12:45 a.m.