Triple
T28501770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess of Sandwich |
E721252
|
entity |
| Predicate | correspondingTitle |
P18605
|
FINISHED |
| Object | Earl of Sandwich |
—
|
NE NERFINISHED |
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: Earl of Sandwich | Statement: [Countess of Sandwich, correspondingTitle, Earl of Sandwich]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondingTitle Context triple: [Countess of Sandwich, correspondingTitle, Earl of Sandwich]
-
A.
associatedTitle
Indicates that one entity has a title, designation, or formal label that is linked or relevant to another entity.
-
B.
equivalentOrRelatedTitle
Indicates that two titles are the same or sufficiently similar in meaning, role, or status to be treated as equivalent or closely related.
-
C.
associatedTitleType
Indicates the type or category of a title that is linked or related to another entity or primary title.
-
D.
relatedTitleHolder
chosen
Indicates that one entity holds a title or position that is related or connected to the title or position held by another entity.
-
E.
commonTitle
Indicates that two or more entities share the same title or designation.
- 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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f67c9fe7b48190b79b4041357edb49 |
completed | May 2, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 28, 2026, 3:07 a.m.