Triple
T10188302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PQ convoys |
E236966
|
entity |
| Predicate | convoyCodePattern |
P42966
|
FINISHED |
| Object | letters PQ followed by number |
—
|
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: letters PQ followed by number | Statement: [PQ convoys, convoyCodePattern, letters PQ followed by number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convoyCodePattern Context triple: [PQ convoys, convoyCodePattern, letters PQ followed by number]
-
A.
convoyCode
chosen
Indicates that an entity is assigned or associated with a specific convoy identification code used for grouping or tracking movements.
-
B.
convoyType
Indicates the specific kind or classification of convoy associated with or used in the relationship between the entities.
-
C.
convoyComposition
Indicates that one entity is composed of, or includes as its members, the set of entities forming a convoy.
-
D.
convoyCargo
Indicates that one entity is transporting or escorting another entity as cargo within a convoy.
-
E.
convoyDestination
Indicates that a convoy is headed toward or assigned to reach a specific destination location.
- 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_69ca84d7260c8190bfbec36762943f37 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cded7c3278819093312665b54d888c |
completed | April 2, 2026, 4:15 a.m. |
| PD | Predicate disambiguation | batch_69cd7c8477648190bc55c56aeec507d3 |
completed | April 1, 2026, 8:13 p.m. |
Created at: March 30, 2026, 9:12 p.m.