Triple
T3585434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bret Saberhagen |
E75897
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Bret |
E305287
|
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: Bret | Statement: [Bret Saberhagen, givenName, Bret]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bret Context triple: [Bret Saberhagen, givenName, Bret]
-
A.
Bret
chosen
Bret is a masculine given name most notably associated with American author and poet Bret Harte.
-
B.
Brett
Brett is the given name of Brett M. Kavanaugh, an Associate Justice of the United States Supreme Court.
-
C.
Garrett
Garrett is a masculine given name of Old French and Germanic origin, commonly used in English-speaking countries.
-
D.
Kurt Buckman
Kurt Buckman is one of the three beleaguered friends in the dark comedy film "Horrible Bosses," known for plotting to kill his abusive employer alongside his equally frustrated coworkers.
-
E.
Brock
Brock is a surname most notably associated with figures such as Isaac Brock, a British Army officer and colonial administrator famed for his leadership in the War of 1812.
- 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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc135ee3481908ef8dc41af632710 |
completed | March 8, 2026, 6:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402fcc5f481909c66319f75a8dc85 |
completed | March 13, 2026, 12:28 p.m. |
Created at: March 8, 2026, 3:22 p.m.