Triple
T15681698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bob Harris |
E377591
|
entity |
| Predicate | residesDuringFilm |
P49534
|
FINISHED |
| Object | luxury Tokyo hotel |
—
|
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: luxury Tokyo hotel | Statement: [Bob Harris, residesDuringFilm, luxury Tokyo hotel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residesDuringFilm Context triple: [Bob Harris, residesDuringFilm, luxury Tokyo hotel]
-
A.
residenceAtStartOfFilm
Indicates the place where a person or character is living at the beginning of the film.
-
B.
placementInFilm
Indicates the specific position or occurrence of something within the sequence or structure of a film.
-
C.
basedInFilm
Indicates that something (such as a character, event, or work) is situated, set, or primarily located within the context or universe of a particular film.
-
D.
residenceDuringEvent
chosen
Indicates that an entity resides or is located at a particular place for the duration of a specified event.
-
E.
visitedInFilm
Indicates that a location or place is depicted as being visited by a character within the events of a film.
- 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_69d85cd2e28481909d4e975bee20872f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04f306a1c8190a819541a3cc51f5a |
completed | April 16, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69deda8b36a4819081cb5708fe77ef51 |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:16 a.m.