Triple
T36407183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basil Hallward's portrait |
E896777
|
entity |
| Predicate | laterLocationInStory |
P42649
|
FINISHED |
| Object | a locked upstairs room in Dorian Gray's house |
—
|
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: a locked upstairs room in Dorian Gray's house | Statement: [Basil Hallward's portrait, laterLocationInStory, a locked upstairs room in Dorian Gray's house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterLocationInStory Context triple: [Basil Hallward's portrait, laterLocationInStory, a locked upstairs room in Dorian Gray's house]
-
A.
laterLocation
chosen
Indicates that an entity is located at a specified place at a later time than some reference time or earlier location.
-
B.
positionInStory
Indicates the point or role an event, character, or element occupies within the overall sequence or structure of a story.
-
C.
inspiredLaterLocation
Indicates that one entity inspired or influenced the choice of a later location associated with another entity.
-
D.
locationOfNarrative
Indicates the place or setting where the events or story described in the narrative occur.
-
E.
immediateAftermathLocation
Indicates the location where the direct and immediate consequences of an event take 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00a846a8f881908b073ad13a5af6ca |
completed | May 10, 2026, 3:46 p.m. |
| PD | Predicate disambiguation | batch_6a00a7aae194819085e1a2fd406f7922 |
completed | May 10, 2026, 3:43 p.m. |
Created at: May 3, 2026, 4:10 p.m.