Triple
T5129332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joseph Joffre |
E115656
|
entity |
| Predicate | promotedToMarshalOfFrance |
P62781
|
FINISHED |
| Object | 1916 |
—
|
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: 1916 | Statement: [Joseph Joffre, promotedToMarshalOfFrance, 1916]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: promotedToMarshalOfFrance Context triple: [Joseph Joffre, promotedToMarshalOfFrance, 1916]
-
A.
promotedToMajorGeneralOfVolunteers
Indicates that a person was elevated in rank to serve as a major general within a volunteer military force.
-
B.
isOldestMilitaryDecorationOf
Indicates that one military decoration is the earliest or first established award within a specified group, organization, or country.
-
C.
isMilitaryDecorationOf
Indicates that something is a military award or honor that has been conferred upon a particular person, unit, or entity.
-
D.
militaryAward
Indicates that an entity has received or been granted a specific military honor, decoration, or award.
-
E.
successorAsEmpressOfTheFrench
Indicates that one person became the next Empress of the French following another person in that imperial role.
- 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_69bd444426bc819099ccd23f141e22aa |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7fef2e8c8190982dd67f50295ada |
completed | March 20, 2026, 5:12 p.m. |
| PD | Predicate disambiguation | batch_69bd77ac2fc48190abeebb003a82384c |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd7fee42748190967013828973cce0 |
completed | March 20, 2026, 5:12 p.m. |
Created at: March 20, 2026, 1:42 p.m.