Triple
T33493998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alice Tan |
E857815
|
entity |
| Predicate | sharesNamesakeHonorWith |
P36445
|
FINISHED |
| Object | Peter Tan |
—
|
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: Peter Tan | Statement: [Alice Tan, sharesNamesakeHonorWith, Peter Tan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesNamesakeHonorWith Context triple: [Alice Tan, sharesNamesakeHonorWith, Peter Tan]
-
A.
sharesSurnameWithMany
Indicates that an entity has the same surname as a large number of other entities.
-
B.
usedAsNamesakeFor
Indicates that one entity serves as the source or inspiration for the name given to another entity.
-
C.
hasHonorificNamesake
Indicates that an entity is named in honor of another entity, serving as a namesake that recognizes or commemorates the other.
-
D.
sharesEponymWith
chosen
Indicates that two entities are named after the same person, place, or thing (i.e., they share the same eponym).
-
E.
hasTitleNamesake
Indicates that one entity serves as the namesake or source of the title borne by another entity.
- 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_69f3497660508190a541826a81f7e9ab |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffab5adf2c819084700c5ea34615bf |
completed | May 9, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69ffaabffa208190b5214ca17cc8a5ea |
completed | May 9, 2026, 9:44 p.m. |
Created at: May 1, 2026, 1:38 a.m.