Triple
T16303309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kounotori |
E395842
|
entity |
| Predicate | referentClass |
P114972
|
FINISHED |
| Object | bird |
—
|
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: bird | Statement: [Kounotori, referentClass, bird]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referentClass Context triple: [Kounotori, referentClass, bird]
-
A.
referenceType
Indicates the specific kind or category of reference relationship that one entity has to another.
-
B.
symbolReferenced
Indicates that one symbol is mentioned, cited, or otherwise referred to by another symbol.
-
C.
possibleTypeOfReferent
chosen
Indicates that something could be a potential or candidate type or category to which a given referent may belong, without asserting that it definitively is that type.
-
D.
refersSpecificallyTo
Indicates that one entity makes an explicit, precise reference to another particular entity, distinguishing it from more general or ambiguous references.
-
E.
requiresReferent
Indicates that one entity depends on or must reference another specific entity in order to be valid, interpretable, or complete.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e35157481909e5604b7dae7a2a2 |
completed | April 17, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.