Triple
T5044850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Convent |
E113636
|
entity |
| Predicate | distanceFromRuby |
P56200
|
FINISHED |
| Object | several miles outside the town (in the novel) |
—
|
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: several miles outside the town (in the novel) | Statement: [the Convent, distanceFromRuby, several miles outside the town (in the novel)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromRuby Context triple: [the Convent, distanceFromRuby, several miles outside the town (in the novel)]
-
A.
distancedFrom
chosen
Indicates that one entity is physically or metaphorically kept at a certain distance or separation from another entity.
-
B.
distanceFromTokyo
Indicates the physical distance between a given location and Tokyo.
-
C.
distanceFromOrange
Indicates the spatial distance between a given entity and an orange as the reference point.
-
D.
distanceCharacteristic
Indicates a relationship where an entity is described or constrained by some property or measure of distance (e.g., range, spacing, or separation).
-
E.
distanceFromToronto
Indicates the spatial distance between a given entity and the location of Toronto.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fd81788190b7799f519277119a |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd71529d608190a53470ba6c14bb1d |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.