Triple
T14591287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stray Feath. |
E342448
|
entity |
| Predicate | possibleTypeOfReferent |
P114972
|
FINISHED |
| Object | publication |
—
|
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: publication | Statement: [Stray Feath., possibleTypeOfReferent, publication]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleTypeOfReferent Context triple: [Stray Feath., possibleTypeOfReferent, publication]
-
A.
referenceType
Indicates the specific kind or category of reference relationship that one entity has to another.
-
B.
hasReferentKnownFor
Indicates that the referent (the thing being referred to) is known or notable for a particular characteristic, role, or achievement.
-
C.
hasTypeOfReference
Indicates that one entity uses or is associated with a particular kind or category of reference (such as a citation, pointer, or referential link) to another entity.
-
D.
hasAlternativeReferent
Indicates that an entity can also be referred to or identified by an alternative name, label, or reference.
-
E.
canReferToMultipleIndividuals
Indicates that a single reference, term, or identifier may correspond to more than one individual rather than uniquely identifying just one.
- F. None of above. chosen
Provenance (4 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4249af08190962009741d1f7d41 |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
| PDg | Predicate description generation | batch_69de716c17cc8190aeb85296abee85a7 |
completed | April 14, 2026, 4:55 p.m. |
Created at: April 10, 2026, 1:24 a.m.