Triple
T29051413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Clarke |
E735268
|
entity |
| Predicate | relationshipToEmilyThorne |
P202769
|
FINISHED |
| Object | source of assumed identity |
—
|
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: source of assumed identity | Statement: [David Clarke, relationshipToEmilyThorne, source of assumed identity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToEmilyThorne Context triple: [David Clarke, relationshipToEmilyThorne, source of assumed identity]
-
A.
relationshipToOdette
Indicates the specific familial, social, or interpersonal connection that an entity has with Odette.
-
B.
relationshipToSamanthaGrimm
Indicates the specific type of relationship or connection an entity has to Samantha Grimm.
-
C.
relationshipToEthanEdwards
Indicates the nature or type of connection, association, or bond that one entity has with Ethan Edwards.
-
D.
relationshipToEvanHansen
Indicates the type or nature of a person's relationship or connection to Evan Hansen.
-
E.
relationshipToSophiaPeletier
Indicates the specific familial, social, or interpersonal connection that an entity has to Sophia Peletier.
- F. None of above. chosen
Provenance (4 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a00b6e163308190adeb1d6eb8558641 |
completed | May 10, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_6a00b67e0e388190b08ad66cee4cb0d7 |
completed | May 10, 2026, 4:46 p.m. |
| PDg | Predicate description generation | batch_6a00b6e0b954819094e63589d718b9af |
completed | May 10, 2026, 4:48 p.m. |
Created at: April 28, 2026, 10:08 a.m.