Triple
T6839896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anzac-class frigate |
E157543
|
entity |
| Predicate | numberBuiltFor |
P2091
|
FINISHED |
| Object | 8 for Royal Australian Navy |
—
|
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: 8 for Royal Australian Navy | Statement: [Anzac-class frigate, numberBuiltFor, 8 for Royal Australian Navy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberBuiltFor Context triple: [Anzac-class frigate, numberBuiltFor, 8 for Royal Australian Navy]
-
A.
numberBuilt
chosen
Indicates the total count of items or structures that have been constructed or produced.
-
B.
isBuiltFor
Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
-
C.
modelNumber
Indicates that one entity is the specific model identifier or code assigned to another entity (such as a product or device).
-
D.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
E.
hasPartNumber
Indicates that one entity is assigned or associated with a specific part number used to identify it within a catalog, system, or inventory.
- 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_69c6882c53608190b99aebef079b23bd |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d6b2ee248190991c3e827be75bb7 |
completed | March 27, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69c6d09f90648190bc0a462c7d59de1b |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:19 p.m.