Triple
T3364073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dorchester Hotel |
E70791
|
entity |
| Predicate | hasNotableGuestType |
P10756
|
FINISHED |
| Object | celebrities |
—
|
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: celebrities | Statement: [The Dorchester Hotel, hasNotableGuestType, celebrities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableGuestType Context triple: [The Dorchester Hotel, hasNotableGuestType, celebrities]
-
A.
hasNotableGuest
chosen
Indicates that an entity has a guest who is distinguished, prominent, or otherwise noteworthy in some significant way.
-
B.
hasNotablePerformer
Indicates that an entity features or is associated with a performer who is particularly prominent, famous, or otherwise noteworthy.
-
C.
hasNotableHost
Indicates that an entity is associated with a host who is particularly prominent, famous, or otherwise noteworthy.
-
D.
hasNotablePatron
Indicates that an entity is significantly supported, sponsored, or championed by a distinguished or influential patron.
-
E.
hasNotableMember
Indicates that a group, organization, or collection includes at least one member who is distinguished or noteworthy in some significant way.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb28467b88190bdf70b851bc8efa9 |
completed | March 8, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69ada4317e288190ab7d0f66e9dba65f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.