Triple
T34162942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pothos |
E876326
|
entity |
| Predicate | closelyRelatedConcept |
P187599
|
FINISHED |
| Object | Eros (romantic love) |
E2080051
|
NE 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: Eros (romantic love) | Statement: [Pothos, closelyRelatedConcept, Eros (romantic love)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closelyRelatedConcept Context triple: [Pothos, closelyRelatedConcept, Eros (romantic love)]
-
A.
moreCloselyRelatedTo
Indicates that one entity has a stronger or closer relationship, connection, or similarity to a second entity than to some other reference entity.
-
B.
definitionOfRelatedConcept
Indicates that one concept provides the formal meaning, explanation, or characterization of another closely related concept.
-
C.
closelyRelatedVariety
Indicates that one variety is very similar to another, differing only in minor or closely related characteristics.
-
D.
functionallyRelatedTo
Indicates that two entities are connected through a functional relationship, where the operation, behavior, or role of one depends on, influences, or complements that of the other.
-
E.
relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
- F. None of above. chosen
Provenance (5 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_69f349ac987481908a8e6053f665bc8b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fb6fdc7eb081908ab8475efb38c430 |
completed | May 6, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36c1d55d30819081eb7818f62bd224 |
completed | June 20, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69fb5a986e588190b7a10892bd2ff44c |
completed | May 6, 2026, 3:13 p.m. |
| PDg | Predicate description generation | batch_69fb6fdab95c81909acff3c6a2359787 |
completed | May 6, 2026, 4:44 p.m. |
Created at: May 1, 2026, 1:54 a.m.