Triple
T4095472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trophy Building |
E87806
|
entity |
| Predicate | tourStopOn |
P35768
|
FINISHED |
| Object | Graceland mansion tour |
—
|
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: Graceland mansion tour | Statement: [Trophy Building, tourStopOn, Graceland mansion tour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourStopOn Context triple: [Trophy Building, tourStopOn, Graceland mansion tour]
-
A.
tourStartingPointSide
Indicates the side or direction from which a tour begins relative to a reference point or route.
-
B.
tourAccess
Indicates that an entity is permitted to participate in, enter, or make use of a specific tour.
-
C.
hasStopNear
chosen
Indicates that one entity has a stop or stopping point located in close proximity to another entity.
-
D.
roundOfStoppage
Indicates the specific round in which a contest, match, or event was stopped or ended prematurely.
-
E.
touristGatewayTo
Indicates a relationship where one place serves as the primary access point or entry hub for tourists visiting another place.
- 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcddd76c81909fbf5db1f5d91a14 |
completed | March 9, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69aef90b2ef08190ae84febfd69dd48b |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:40 p.m.