Triple
T27969539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lara Stone |
E706315
|
entity |
| Predicate | walkedFor |
P163582
|
FINISHED |
| Object | Victoria's Secret Fashion Show |
—
|
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: Victoria's Secret Fashion Show | Statement: [Lara Stone, walkedFor, Victoria's Secret Fashion Show]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: walkedFor Context triple: [Lara Stone, walkedFor, Victoria's Secret Fashion Show]
-
A.
walkedAheadOf
Indicates that one entity moved forward on a path or route in front of another entity, leading or preceding them in walking.
-
B.
wentToDistance
Indicates that an entity traveled to or reached a specified distance from a reference point.
-
C.
wentTheDistance
Indicates that an entity persisted through an entire challenge, task, or event without giving up or stopping early.
-
D.
hasWalkingRouteType
Indicates that an entity is associated with a specific type or category of walking route (e.g., trail, path, or walking itinerary).
-
E.
walkThrough
Indicates moving through or along the interior or extent of something, typically traversing a space or environment from one side or point to another.
- 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_69ef96b7f330819090f315318ba6977e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63b3416f08190b23151dc2be33f1e |
completed | May 2, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 7:37 p.m.