Triple
T8963460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Gardner |
E214065
|
entity |
| Predicate | isAmbiguousNameFor |
P71696
|
FINISHED |
| Object | multiple notable individuals |
—
|
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: multiple notable individuals | Statement: [Mark Gardner, isAmbiguousNameFor, multiple notable individuals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAmbiguousNameFor Context triple: [Mark Gardner, isAmbiguousNameFor, multiple notable individuals]
-
A.
isAmbiguousName
chosen
Indicates that a name can refer to multiple distinct entities or interpretations, making its reference unclear without additional context.
-
B.
namedForConflict
Indicates that one entity is named after, or in commemoration of, a specific conflict, war, or battle.
-
C.
isRelatedName
Indicates that one name is connected to another through a variant, derivative, or otherwise non-identical but related naming relationship.
-
D.
isEarlyNameOf
Indicates that one name is an earlier or former designation for the same entity as another name.
-
E.
hasNoWidelyUsedLocalName
Indicates that the entity does not have a commonly used or widely recognized name in the local language or region.
- 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_69ca839cd6008190a1546a701a56710c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc674b06f08190b2d992674a093592 |
completed | April 1, 2026, 12:31 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed74d288190b712d739805579dc |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:01 p.m.