Triple
T33190887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claire Littleton |
E849606
|
entity |
| Predicate | portrayedInFlashSidewaysBy |
P197746
|
FINISHED |
| Object | Emilie de Ravin |
—
|
NE NERFINISHED |
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: Emilie de Ravin | Statement: [Claire Littleton, portrayedInFlashSidewaysBy, Emilie de Ravin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedInFlashSidewaysBy Context triple: [Claire Littleton, portrayedInFlashSidewaysBy, Emilie de Ravin]
-
A.
portrayedInFlashbacks
Indicates that an entity appears or is depicted specifically within flashback scenes of a narrative work.
-
B.
companionActorInFlashback
Indicates that one actor appears as a companion to another actor specifically within a flashback sequence.
-
C.
portrayedByInSpinOff
Indicates that an entity is portrayed by a particular actor specifically in a spin-off production related to the original work.
-
D.
portrayedByInSequel
Indicates that an entity is portrayed by a particular actor or performer specifically in a sequel work (e.g., a sequel film, series, or game).
-
E.
portrayedSurvivorOf
Indicates that one entity depicted or represented another entity as a survivor of a particular event, situation, or condition.
- 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_69f3495e0f108190a6a7006f79f9c2c3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fea5e828cc8190a9b755a645dc56d2 |
completed | May 9, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69fea36443f08190b2aced9b4a0525fd |
completed | May 9, 2026, 3 a.m. |
| PDg | Predicate description generation | batch_69fea5e75a5481908a04d91ee7255ebb |
completed | May 9, 2026, 3:11 a.m. |
Created at: May 1, 2026, 1:29 a.m.