Triple
T19181305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tim Robbins |
E469579
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Mary Robbins |
E469579
|
NE 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: Mary Robbins | Statement: [Tim Robbins, mother, Mary Robbins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Robbins Context triple: [Tim Robbins, mother, Mary Robbins]
-
A.
Mary Robbins
chosen
Mary Robbins is known as the mother of American actor and filmmaker Tim Robbins.
-
B.
Mary Easty
Mary Easty was a respected Salem, Massachusetts woman who was falsely accused of witchcraft and executed during the 1692 Salem witch trials, later remembered for her dignified plea for justice.
-
C.
Ruth Robbins
Ruth Robbins is an academic and author known for her work in literary and cultural studies.
-
D.
Ruth Robbins
Ruth Robbins was an American illustrator best known for her artwork in classic fantasy literature, including the original edition of Ursula K. Le Guin’s "A Wizard of Earthsea."
-
E.
Sarah Morrisett
Sarah Morrisett is the daughter of Lloyd Morrisett, the co-creator of the pioneering educational television program "Sesame Street."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f61be86c81908710341262e911cd |
completed | April 20, 2026, 9:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a096da3b8e88190bae1daccb216d35a |
completed | May 17, 2026, 7:26 a.m. |
Created at: April 10, 2026, 12:07 p.m.