Triple
T29066533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moonlighting |
E735688
|
entity |
| Predicate | mainCouple |
P152718
|
FINISHED |
| Object | Maddie Hayes and David Addison Jr. |
—
|
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: Maddie Hayes and David Addison Jr. | Statement: [Moonlighting, mainCouple, Maddie Hayes and David Addison Jr.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCouple Context triple: [Moonlighting, mainCouple, Maddie Hayes and David Addison Jr.]
-
A.
hasMainCouple
chosen
Indicates that a work or narrative features a primary romantic couple who are the central focus of its relationship storyline.
-
B.
couplesTo
Indicates that one entity is joined or linked to another in a way that allows interaction, transfer, or mutual influence between them.
-
C.
spouseInDuo
Indicates that two individuals are spouses who perform or appear together as a duo.
-
D.
couplesQuarks
Indicates an interaction or relationship in which quarks are linked or coupled to each other or to another entity through a fundamental force or mechanism.
-
E.
principalWifeOf
Indicates that one person is the primary or main wife of another person, typically among multiple spouses.
- 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_69f077e85498819088b65186550da8cd |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 28, 2026, 10:18 a.m.