Triple
T36504978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Protapirus |
E899435
|
entity |
| Predicate | hasDescendantTaxon |
P32608
|
FINISHED |
| Object | Tapirus |
—
|
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: Tapirus | Statement: [Protapirus, hasDescendantTaxon, Tapirus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDescendantTaxon Context triple: [Protapirus, hasDescendantTaxon, Tapirus]
-
A.
hasSubtaxon
chosen
Indicates that one taxonomic group is a subordinate or included taxon within another taxonomic group.
-
B.
hasRelatedTaxon
Indicates a taxonomic relationship between two taxa that are connected in some biologically or taxonomically relevant way, without specifying the exact nature of that relationship.
-
C.
hasMemberTaxonRank
Indicates that a group or higher-level taxon includes members classified at a specified taxonomic rank.
-
D.
alsoHasAncestry
Indicates that an entity possesses an additional ancestral lineage or heritage beyond its primary recorded ancestry.
-
E.
hasAncestralTo
Indicates that one entity is an ancestor of another, existing in an earlier generation within a lineage or heritage chain.
- 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_69f76e5b92088190933afda3f7531dd4 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff779e3f0c8190a861f1e4000fd9d9 |
completed | May 9, 2026, 6:06 p.m. |
| PD | Predicate disambiguation | batch_69ff77202638819086e4b9f9c0bc7b31 |
completed | May 9, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:10 p.m.