Triple
T15060163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mare Sheehan |
E379603
|
entity |
| Predicate | hasExSpouse |
P23411
|
FINISHED |
| Object | Frank Sheehan |
E1203655
|
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: Frank Sheehan | Statement: [Mare Sheehan, hasExSpouse, Frank Sheehan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Sheehan Context triple: [Mare Sheehan, hasExSpouse, Frank Sheehan]
-
A.
Frank Sheehan
chosen
Frank Sheehan is a character in the television series "Mare of Easttown," known as the ex-husband of the main protagonist, Mare Sheehan, and a central figure in her complex family dynamics.
-
B.
Ed McLaughlin
Ed McLaughlin is an American college athletics administrator best known as the athletic director at Virginia Commonwealth University (VCU).
-
C.
Lyndon Sheehan
Lyndon Sheehan is a New Zealand film producer known for his work on several notable local and international productions.
-
D.
Bill Heelan
Bill Heelan is a developer best known for creating the software project Archie.
-
E.
Frank Corrigan
Frank Corrigan is a relatively obscure individual whose name is notable primarily for its appearance in records or references rather than for widely recognized public achievements.
- 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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedee50afc8190bf7b0f4bbe8c60a3 |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014819dfbc8190b39a10647f9ba64c |
completed | May 11, 2026, 3:08 a.m. |
Created at: April 10, 2026, 3:01 a.m.