Triple
T24152679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilly Moscovitz |
E598580
|
entity |
| Predicate | relationshipToMiaThermopolis |
P152698
|
FINISHED |
| Object | best friend |
—
|
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: best friend | Statement: [Lilly Moscovitz, relationshipToMiaThermopolis, best friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToMiaThermopolis Context triple: [Lilly Moscovitz, relationshipToMiaThermopolis, best friend]
-
A.
relationshipStatusWithMiaThermopolis
chosen
Indicates the type or state of a subject’s interpersonal relationship with Mia Thermopolis.
-
B.
relationshipToMichelle
Indicates the specific type of relationship or connection that an entity has to Michelle.
-
C.
relationshipToTinaBordereau
Indicates the specific type of personal or professional relationship an entity has with Tina Bordereau.
-
D.
relationshipToParis
Indicates the specific type of connection or association an entity has with Paris.
-
E.
relationshipToPawneeNation
Indicates the specific type of familial, legal, historical, or political relationship that an entity has with the Pawnee Nation.
- 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_69e288c9e488819093dd1acd91b08b8a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e0e1e5748190bcc6681d409dcc05 |
completed | April 29, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_69f176585f3481909beb907de252cd98 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:30 p.m.