Triple
T35198440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brendan McDonough (Only the Brave) |
E1016331
|
entity |
| Predicate | developsBondWith |
P68132
|
FINISHED |
| Object | Eric Marsh (Only the Brave) |
—
|
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: Eric Marsh (Only the Brave) | Statement: [Brendan McDonough (Only the Brave), developsBondWith, Eric Marsh (Only the Brave)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developsBondWith Context triple: [Brendan McDonough (Only the Brave), developsBondWith, Eric Marsh (Only the Brave)]
-
A.
bondedWith
chosen
Indicates that two entities are joined by a strong, enduring connection or attachment, whether emotional, social, or structural.
-
B.
canBondWith
Indicates that one entity has the capability or compatibility to form a bond or connection with another entity.
-
C.
relationshipToBond
Indicates the specific type of personal, familial, or professional relationship an entity has to the person named Bond.
-
D.
pairBond
Indicates a long-term, typically exclusive social or reproductive partnership formed between two individuals.
-
E.
typicalBonding
Indicates a usual or characteristic bonding relationship that commonly occurs between the involved entities.
- 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_69f76dde814c8190a71f60d514a424a4 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd474b7e788190a9bb9b542d878f60 |
completed | May 8, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69fd46d8b2f0819099d92d72c902f60e |
completed | May 8, 2026, 2:13 a.m. |
Created at: May 3, 2026, 4:02 p.m.