Triple
T4346960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Lieutenant |
E97927
|
entity |
| Predicate | typicalPromotionTo |
P8176
|
FINISHED |
| Object | Captain |
—
|
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: Captain | Statement: [First Lieutenant, typicalPromotionTo, Captain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPromotionTo Context triple: [First Lieutenant, typicalPromotionTo, Captain]
-
A.
promotesFrom
Indicates that one entity advances or elevates another entity from a lower position, role, or status to a higher one.
-
B.
promotionTo
chosen
Indicates that one entity is elevated or advanced to a higher rank, position, or status relative to another entity or context.
-
C.
allowsPromotion
Indicates that one entity grants permission or enables another entity to be promoted to a higher status, level, or position.
-
D.
hasPromotionFrom
Indicates that an entity receives or is associated with a promotion that originates from a specified source entity (such as a campaign, organization, or person).
-
E.
typicalTimeInRankBeforePromotion
Indicates the usual duration an individual spends in a given rank or position before being promoted to the next level.
- 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_69b34548402c819085ab68b27c235a87 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3518d6728819084a2f40ae0bd3ac8 |
completed | March 12, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69b34f4fe1c481908d6d66e15697c04b |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:15 p.m.