Triple
T10908856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Mullally |
E257639
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Mullally |
E257639
|
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: Mullally | Statement: [James Mullally, familyName, Mullally]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mullally Context triple: [James Mullally, familyName, Mullally]
-
A.
Mullally
chosen
Mullally is a surname of Irish origin borne by various notable individuals in fields such as entertainment, sports, and public service.
-
B.
Mullane
Mullane is a surname of Irish origin, considered a variant of the name Mullen.
-
C.
Mulcahy
Mulcahy is an Irish surname of Gaelic origin, borne by various notable figures in Ireland and the Irish diaspora.
-
D.
Killoscully
Killoscully is a small rural village in Ireland known for its scenic countryside and traditional community character.
-
E.
Dignam
Dignam is a sharp-tongued, tough-as-nails police sergeant in the crime thriller film "The Departed," known for his brutal honesty and volatile temper.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7706824d08190ba894d144cc6b3ba |
completed | April 9, 2026, 9:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a92e09648190ab39053521211743 |
completed | April 18, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:22 p.m.