Triple
T13864480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Ehrlich |
E333285
|
entity |
| Predicate | hasGivenName |
P17
|
FINISHED |
| Object | Walter |
E32053
|
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: Walter | Statement: [Walter Ehrlich, hasGivenName, Walter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walter Context triple: [Walter Ehrlich, hasGivenName, Walter]
-
A.
Walter
chosen
Walter is a masculine given name of Germanic origin that has been widely used in English-speaking countries.
-
B.
Walter
Walter is a grumpy, sharp-tongued old-man puppet character featured in Jeff Dunham’s stand-up comedy acts.
-
C.
Walter Haut
Walter Haut was a former U.S. Army Air Force public information officer best known for issuing the 1947 Roswell UFO press release and later co-founding the International UFO Museum and Research Center.
-
D.
Wilbert
Wilbert is the given first name of American character actor Bill Cobbs, known for his numerous supporting roles in film and television.
-
E.
Wally Fay
Wally Fay is a supporting character in the 1945 film noir "Mildred Pierce," known as a somewhat sleazy businessman entangled in the story’s web of betrayal and murder.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de05c30d9c81908217d41a3b4aaf85 |
completed | April 14, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c10113288190b799126d934df92a |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:14 p.m.