Triple
T22021465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilda Dent |
E543854
|
entity |
| Predicate | hasCanonicalConnectionTo |
P8776
|
FINISHED |
| Object | Harvey Dent’s disfigurement |
—
|
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: Harvey Dent’s disfigurement | Statement: [Gilda Dent, hasCanonicalConnectionTo, Harvey Dent’s disfigurement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanonicalConnectionTo Context triple: [Gilda Dent, hasCanonicalConnectionTo, Harvey Dent’s disfigurement]
-
A.
hasCanonicalReference
Indicates that one entity serves as the authoritative or standard reference source for another entity.
-
B.
hasAccessibleConnection
Indicates that there exists a way for one entity to reach or interact with another in a manner that meets defined accessibility requirements.
-
C.
hasCanonicalContext
Indicates that something is associated with its primary, standard, or officially recognized contextual setting or framework.
-
D.
hasConnection
chosen
Indicates that there exists a link, association, or relationship between two entities.
-
E.
hasConnector
Indicates that one entity is linked or joined to another entity through a connector or connecting element.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c7b3308190ac056bef6f82722e |
completed | April 28, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:23 p.m.