Triple
T20017384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philip IV of France |
E494757
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Philip |
—
|
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: Philip | Statement: [Philip IV of France, givenName, Philip]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philip Context triple: [Philip IV of France, givenName, Philip]
-
A.
Philip
Philip is the given name of Philip Sheridan, a prominent Union general in the American Civil War who later became Commanding General of the U.S. Army.
-
B.
Philip
chosen
Philip was the given name of Philip IV of France, the medieval Capetian king known for his conflicts with the papacy and the suppression of the Knights Templar.
-
C.
Philip
Philip is one of the middle names of William Arthur Philip Louis, better known as Prince William, the heir apparent to the British throne.
-
D.
Philip
Philip is the given name of Philip H. Lathrop, an American cinematographer known for his work on numerous Hollywood films.
-
E.
Philip
Philip is the given name of Philip Barton Key II, the 19th-century U.S. Attorney for the District of Columbia whose 1859 murder by Congressman Daniel Sickles became a landmark legal case.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6623d76808190988990a8dc263ef7 |
completed | April 20, 2026, 5:28 p.m. |
Created at: April 11, 2026, 3:34 p.m.