Triple
T31922219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiraman |
E814999
|
entity |
| Predicate | hasPhylumAssignment |
P34103
|
FINISHED |
| Object | Papuan (broad areal grouping) |
—
|
NE NERFINISHED |
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: Papuan (broad areal grouping) | Statement: [Kiraman, hasPhylumAssignment, Papuan (broad areal grouping)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPhylumAssignment Context triple: [Kiraman, hasPhylumAssignment, Papuan (broad areal grouping)]
-
A.
hasPhylum
chosen
Indicates that an entity (typically a biological taxon or organism) is classified as belonging to a particular phylum in a taxonomic hierarchy.
-
B.
hasSubphylum
Indicates that one biological entity is classified as a subphylum within the broader taxonomic grouping of another entity.
-
C.
hasTaxonomicRankAbove
Indicates that one taxonomic rank is hierarchically higher (more inclusive) than another in a classification system.
-
D.
hasTaxonomicRankBelow
Indicates that one taxonomic rank is hierarchically lower (more specific) than another within a classification system.
-
E.
hasSubkingdom
Indicates that one biological kingdom is divided into, or associated with, a specific subkingdom as a subordinate taxonomic rank.
- 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_69f348f1df848190851bbfb988da3414 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 12:03 a.m.