Triple
T28884459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aqueduct of Maintenon |
E732515
|
entity |
| Predicate | destinationIntended |
P885
|
FINISHED |
| Object | Palace of Versailles |
—
|
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: Palace of Versailles | Statement: [Aqueduct of Maintenon, destinationIntended, Palace of Versailles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destinationIntended Context triple: [Aqueduct of Maintenon, destinationIntended, Palace of Versailles]
-
A.
destinationOfVoyageTo
Indicates the endpoint location that a particular voyage or journey is directed toward or arrives at.
-
B.
attemptedDestination
Indicates that an entity made an effort to reach or go to a particular destination, regardless of whether the attempt was successful.
-
C.
directedTo
Indicates that something is sent, aimed, or addressed toward a particular target or recipient.
-
D.
transportGoal
Indicates that an entity has the objective or intended outcome of moving or conveying something or someone from one place to another.
-
E.
originalDestination
chosen
Indicates the initial or intended destination associated with an entity before any changes, rerouting, or redirection occur.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65b14512c8190a40e70319dcc54cd |
completed | May 2, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 7:48 a.m.