Triple
T7206238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diprotodon |
E148672
|
entity |
| Predicate | largestKnown |
P72583
|
FINISHED |
| Object | marsupial |
—
|
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: marsupial | Statement: [Diprotodon, largestKnown, marsupial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: largestKnown Context triple: [Diprotodon, largestKnown, marsupial]
-
A.
largestKnownMembers
chosen
Indicates that the related entities are the largest known members within a specified group, category, or set.
-
B.
largestLiving
Indicates that the subject is the largest currently living instance of a given type or within a specified group or context.
-
C.
hasLargestSpecies
Indicates that one entity possesses, contains, or is associated with the species that is largest in size or extent within a given group or context.
-
D.
oneOfLargest
Indicates that the subject is among the largest members within a specified group or set, but not necessarily the single largest.
-
E.
largestSpan
Indicates that the referenced entity has the greatest extent or coverage (in distance, time, or range) among a set of comparable spans.
- 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_69c687e8cf188190b5f3ecffd681f04e |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e94ef5cc81908c33adcedf5c5054 |
completed | March 27, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69c6e757fed4819091b0a096e3befc3a |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:52 p.m.