Triple
T2365383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Entrance |
E47365
|
entity |
| Predicate | hasGesture |
P16866
|
FINISHED |
| Object | sign of the cross with the Gospel Book |
—
|
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: sign of the cross with the Gospel Book | Statement: [Little Entrance, hasGesture, sign of the cross with the Gospel Book]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGesture Context triple: [Little Entrance, hasGesture, sign of the cross with the Gospel Book]
-
A.
hasTouchControls
Indicates that an entity supports or is operated through touch-based input controls.
-
B.
signatureGesture
Indicates a distinctive or characteristic gesture that is uniquely associated with a particular individual or entity.
-
C.
hasGripType
Indicates that one entity possesses or uses a specific type or style of grip in relation to another entity or action.
-
D.
hasChoreographer
Indicates that one entity serves as the choreographer responsible for designing or directing the movement or dance for another entity.
-
E.
gesture
chosen
Indicates that an entity uses a bodily movement or sign to communicate or express something to another entity.
- 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_69a88a1a4a6081908645b0f2914521ab |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc7486cb48190acef1891cc87bdb1 |
completed | March 7, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69abc599b92c819093d9e15d4437705d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:55 p.m.