Triple
T21828151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard T. Markey |
E538910
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Markey |
—
|
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: Markey | Statement: [Howard T. Markey, familyName, Markey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Markey Context triple: [Howard T. Markey, familyName, Markey]
-
A.
Markey
chosen
Markey is a surname most notably associated with American author, screenwriter, and producer Gene Markey.
-
B.
Kitzhaber
Kitzhaber is the surname of John Kitzhaber, an American politician and former governor of Oregon.
-
C.
Pascrell
Pascrell is the surname of Bill Pascrell, an American politician who has served as a U.S. Representative from New Jersey.
-
D.
Patrick M. Murray
Patrick M. Murray is an academic leader who has served as chancellor of Seton Hall University, overseeing its institutional and educational mission.
-
E.
Arlen
Arlen is a given name most notably borne by Arlen Specter, a long-serving United States Senator from Pennsylvania.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c475038c8190abb9b1a20eb8ff50 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f09133718081909faa67c3721aed52 |
completed | April 28, 2026, 10:51 a.m. |
Created at: April 16, 2026, 6:54 p.m.