Triple
T3714700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On the Genealogy of Morality |
E81497
|
entity |
| Predicate | firstEssayTitle |
P33750
|
FINISHED |
| Object | ‘Good and Evil’, ‘Good and Bad’ |
—
|
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: ‘Good and Evil’, ‘Good and Bad’ | Statement: [On the Genealogy of Morality, firstEssayTitle, ‘Good and Evil’, ‘Good and Bad’]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstEssayTitle Context triple: [On the Genealogy of Morality, firstEssayTitle, ‘Good and Evil’, ‘Good and Bad’]
-
A.
firstTitleFor
Indicates that one entity is the earliest or primary title assigned to another entity, typically among multiple possible titles.
-
B.
firstPartTitle
chosen
Indicates that one entity is the first part or initial segment of the title of another entity.
-
C.
firstTitleSince
Indicates that an entity has achieved a particular title for the first time since a specified earlier point, event, or prior title occurrence.
-
D.
firstReleaseTitle
Indicates the title associated with an entity’s initial or earliest release.
-
E.
firstVideoTitle
Indicates the title of the first video associated with an entity in a sequence or collection.
- 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_69ad8b1a81588190b3f27a5483bb610e |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc9ce253c8190ada8eaa395fd3d5c |
completed | March 8, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69adc041a8608190a2d543dab6d2ef6c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:33 p.m.