Triple
T4838301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Inspector-General of the Royal Air Force |
E108116
|
entity |
| Predicate | typicallyHeldByRank |
P7007
|
FINISHED |
| Object | air marshal |
—
|
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: air marshal | Statement: [Inspector-General of the Royal Air Force, typicallyHeldByRank, air marshal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyHeldByRank Context triple: [Inspector-General of the Royal Air Force, typicallyHeldByRank, air marshal]
-
A.
typicallyHoldsRank
chosen
Indicates that an entity is most commonly or usually associated with holding a particular rank or level in a hierarchy.
-
B.
eligibleRank
Indicates that an entity meets the required rank or level criteria to qualify for a specific role, action, or benefit.
-
C.
highestRankIn
Indicates that one entity holds the top or most senior rank within a specified group, category, or context relative to other entities.
-
D.
attendanceRank
Indicates the relative position or level of an entity in terms of how frequently or consistently it attends compared to others.
-
E.
representsRank
Indicates that one entity serves as the rank, status, or hierarchical level assigned to another entity.
- 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_69bd43fbe444819085cb970706ef73f7 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c21c7f08190846049d31fdfa144 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:25 p.m.