Triple
T4777405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Macmillan |
E106083
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Harold |
E9958
|
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: Harold | Statement: [Harold Macmillan, givenName, Harold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harold Context triple: [Harold Macmillan, givenName, Harold]
-
A.
Harold
chosen
Harold is a masculine given name of Old English origin, historically borne by several notable figures including kings and modern public personalities.
-
B.
Harold Crick
Harold Crick is the meticulous IRS auditor and unsuspecting protagonist of the metafictional film "Stranger Than Fiction," whose life begins mirroring a narrated novel.
-
C.
Gerald
Gerald is the birth name of Jerry Brown, the longtime Democratic politician and former governor of California.
-
D.
Gerald
Gerald is the middle name of Stephen G. Breyer, a former Associate Justice of the United States Supreme Court.
-
E.
Gerald
Gerald is a masculine given name of Germanic origin, commonly used in English-speaking countries.
- 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_69bd43f3074c8190937e7b0a457fe9f1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd65881e2c8190aa5b57759885b2bb |
completed | March 20, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43caec588190880c47f11d3f2daf |
completed | March 21, 2026, 7:07 a.m. |
Created at: March 20, 2026, 1:21 p.m.