Triple
T23477353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How I Met Your Father |
E570298
|
entity |
| Predicate | portraysOlderVersionOf |
P144800
|
FINISHED |
| Object | Sophie |
—
|
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: Sophie | Statement: [How I Met Your Father, portraysOlderVersionOf, Sophie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysOlderVersionOf Context triple: [How I Met Your Father, portraysOlderVersionOf, Sophie]
-
A.
isYoungerVersionOf
chosen
Indicates that one entity represents the same individual as another entity, but at an earlier, younger stage in their life.
-
B.
isVersionOf
Indicates that one entity is a particular version, edition, or variant derived from another entity.
-
C.
hasEarlierVersion
Indicates that one entity is an earlier or prior version of another entity in a version sequence.
-
D.
backportedTo
Indicates that a change, feature, or fix originally made in a newer version has been applied retroactively to an older version.
-
E.
earlierVersionsCapability
Indicates that an entity has the ability to access, handle, or interact with earlier versions of another entity or resource.
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69f0620ac3608190b36916261ea50f54 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:01 p.m.