Triple
T29135147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phaedrus |
E738493
|
entity |
| Predicate | firstPartTopic |
P202586
|
FINISHED |
| Object | erotic love and speeches on love |
—
|
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: erotic love and speeches on love | Statement: [Phaedrus, firstPartTopic, erotic love and speeches on love]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPartTopic Context triple: [Phaedrus, firstPartTopic, erotic love and speeches on love]
-
A.
firstPartTitle
Indicates that one entity is the first part or initial segment of the title of another entity.
-
B.
secondPartTopic
Indicates that the second part of a multi-part work, message, or structure is about or focused on a specified topic.
-
C.
firstPartSeries
Indicates that one entity is the initial installment or beginning segment in a series of related entities.
-
D.
primaryTopicOf
Indicates that a given subject is the main or central topic described by another resource (such as a document, page, or record).
-
E.
firstPartType
Indicates that one entity is the initial segment or component type within a larger composite or sequence of parts.
- 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_6a009d623f6c8190b702e2892c52fbb2 |
completed | May 10, 2026, 2:59 p.m. |
| PD | Predicate disambiguation | batch_6a009a3050d48190b64567f28e6ea463 |
completed | May 10, 2026, 2:46 p.m. |
| PDg | Predicate description generation | batch_6a009d6144d48190889bc704368d8878 |
completed | May 10, 2026, 2:59 p.m. |
Created at: April 28, 2026, 11:33 a.m.