Triple
T9923973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bat Masterson |
E187874
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Masterson |
E187874
|
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: Masterson | Statement: [Bat Masterson, familyName, Masterson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Masterson Context triple: [Bat Masterson, familyName, Masterson]
-
A.
Masterson
chosen
Masterson is a surname most famously associated with Bat Masterson, the Old West lawman, gambler, and sportswriter.
-
B.
Mastro
Mastro is an Ontology-Based Data Access (OBDA) system that enables querying relational data sources through an ontology layer using high-level semantic queries.
-
C.
Comiskey
Comiskey is a surname most famously associated with Charles Comiskey, the influential early owner of the Chicago White Sox and a key figure in the development of professional baseball.
-
D.
Morrisen
Morrisen is an alternative spelling or variant form of the surname Morrison.
-
E.
McCaskey
McCaskey is the surname of Virginia Halas McCaskey, the longtime principal owner of the NFL’s Chicago Bears and daughter of legendary coach and owner George Halas.
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb59733188190900426e4e29ae5e3 |
completed | April 2, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20e0bdae08190acb94fe7d5471e4b |
completed | April 5, 2026, 7:23 a.m. |
Created at: March 30, 2026, 8:43 p.m.