Triple
T36407448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lily Frankenstein |
E896784
|
entity |
| Predicate | firstAppearanceAsLily |
P204861
|
FINISHED |
| Object | Penny Dreadful Season 2 |
E47464
|
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: Penny Dreadful Season 2 | Statement: [Lily Frankenstein, firstAppearanceAsLily, Penny Dreadful Season 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstAppearanceAsLily Context triple: [Lily Frankenstein, firstAppearanceAsLily, Penny Dreadful Season 2]
-
A.
firstAppearanceMa
Indicates that an entity (such as a character or item) makes its first appearance in a specific manga.
-
B.
firstAppearanceAsIdentityUser
Indicates the event or context in which a user first appears or is introduced under a particular identity.
-
C.
firstStageAppearance
Indicates the event or context in which an entity makes its initial appearance on stage.
-
D.
firstPopularAppearance
Indicates the earliest notable or widely recognized appearance of an entity in a public or popular context.
-
E.
firstAppearanceApprox
Indicates that one entity is the approximate or estimated first appearance of another entity in time or context.
- 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39c4062d308190894ac57a60a0f0d6 |
completed | June 22, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82f8c88190bd77a086023ac0e1 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:10 p.m.