Triple
T19334140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slave Children’s Crusade |
E483575
|
entity |
| Predicate | underscoresScene |
P107448
|
FINISHED |
| Object | Indiana Jones rescuing enslaved children |
—
|
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: Indiana Jones rescuing enslaved children | Statement: [Slave Children’s Crusade, underscoresScene, Indiana Jones rescuing enslaved children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underscoresScene Context triple: [Slave Children’s Crusade, underscoresScene, Indiana Jones rescuing enslaved children]
-
A.
scenes
chosen
Indicates that one entity is a scene or setting in which the other entity occurs, appears, or is depicted.
-
B.
partOfScene
Indicates that one entity functions as a component or element within a larger scene or setting involving another entity.
-
C.
centralScene
Indicates that one scene functions as the main or focal scene within a larger narrative, sequence, or composition.
-
D.
underlines
Indicates that one entity draws or applies a line beneath another entity, typically to emphasize or highlight it.
-
E.
sceneLabel
Indicates the categorical label or type assigned to an entire scene based on its overall content or context.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e61643f7b8819088a716e54a579afa |
completed | April 20, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_69e4dd12303c8190a2027c062b2dff40 |
completed | April 19, 2026, 1:48 p.m. |
Created at: April 10, 2026, 1:33 p.m.