Triple
T16264623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abram Stevens Hewitt |
E394842
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hewitt |
E188670
|
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: Hewitt | Statement: [Abram Stevens Hewitt, familyName, Hewitt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hewitt Context triple: [Abram Stevens Hewitt, familyName, Hewitt]
-
A.
Hewitt
A Hewitt is a classification for hills in England, Wales, and Ireland that are at least 2,000 feet high with a minimum prominence of 30 meters, commonly used by peak baggers and hillwalkers.
-
B.
Hewitt
Hewitt is a locality or settlement associated with a High Street, likely serving as a small town or neighborhood center.
-
C.
Hewitt
chosen
Hewitt is a surname and given name shared by various notable individuals across fields such as entertainment, sports, and academia.
-
D.
Lem Hewitt
Lem Hewitt is a socially awkward but brilliant research scientist at the morally dubious Veridian Dynamics corporation in the satirical TV sitcom "Better Off Ted."
-
E.
Aon Hewitt
Aon Hewitt is a global human resources consulting and outsourcing firm known for its work in benefits, talent, and retirement solutions.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c73944819085633e6d2a69bae9 |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017b877088190893a1f012e5d2463 |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:05 a.m.