Triple
T8688708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Expo Porte de Versailles |
E206230
|
entity |
| Predicate | hasHotelsOnSite |
P84196
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Paris Expo Porte de Versailles, hasHotelsOnSite, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHotelsOnSite Context triple: [Paris Expo Porte de Versailles, hasHotelsOnSite, yes]
-
A.
hasResortHotel
Indicates that one entity owns, includes, or is associated with a resort hotel as part of its facilities or offerings.
-
B.
hasTourismWebsite
Indicates that an entity has an associated official website specifically dedicated to providing tourism-related information about it.
-
C.
hasNumberOfCampsites
Indicates the specific quantity of campsites associated with a given place, facility, or area.
-
D.
hasHotelType
Indicates that a hotel is classified as belonging to a specific type or category (e.g., resort, boutique, hostel).
-
E.
hasCampSites
Indicates that one entity provides, contains, or is associated with one or more designated camping sites for use.
- 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_69ca835481fc819084e33d3bc883bfa6 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc57334b0c8190903a5a1784e74791 |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc4569f9048190b9c86b4c81103d35 |
completed | March 31, 2026, 10:06 p.m. |
| PDg | Predicate description generation | batch_69cc483f06f48190879f4702c8b4ed00 |
completed | March 31, 2026, 10:18 p.m. |
Created at: March 30, 2026, 6:33 p.m.