Triple
T15014516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhynchocephalia |
E377923
|
entity |
| Predicate | onlyLivingRepresentativeCommonName |
P8591
|
FINISHED |
| Object | tuatara |
—
|
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: tuatara | Statement: [Rhynchocephalia, onlyLivingRepresentativeCommonName, tuatara]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onlyLivingRepresentativeCommonName Context triple: [Rhynchocephalia, onlyLivingRepresentativeCommonName, tuatara]
-
A.
commonName
Indicates that one entity is the commonly used or vernacular name by which the other entity is known.
-
B.
otherCommonName
Indicates that an entity is known by an additional, alternative common name besides its primary one.
-
C.
commonNameOf
Indicates that one entity is the commonly used or popular name by which the other entity is known.
-
D.
recognizedAsRepresentativeBy
Indicates that one entity is acknowledged or accepted by another entity as acting as its representative.
-
E.
notableMemberCommonName
chosen
Indicates that the object is the commonly used or well-known name of a notable member associated with the subject.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7623c3c819092ca36b358b01842 |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:55 a.m.