Triple
T3812669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Kong franchise |
E93170
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Ann Darrow |
E308967
|
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: Ann Darrow | Statement: [King Kong franchise, hasCharacter, Ann Darrow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Darrow Context triple: [King Kong franchise, hasCharacter, Ann Darrow]
-
A.
Ann Darrow
chosen
Ann Darrow is the fictional leading lady and damsel-in-distress from the King Kong franchise, best known as the woman whom the giant ape becomes infatuated with.
-
B.
Florence Cameron
Florence Cameron is the daughter of former UK Prime Minister David Cameron and businesswoman Samantha Cameron.
-
C.
Kate Reed
Kate Reed is the sharp, idealistic former lawyer turned mediator at the center of the legal dramedy series "Fairly Legal."
-
D.
Rose Allerton
Rose Allerton was a member of the early 17th-century Allerton family associated with the Pilgrim settlers of Plymouth Colony.
-
E.
Helen Flint
Helen Flint is a television and film producer known for her work as an executive producer on high-profile drama series.
- 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_69aed96a60088190ab1df8390fffc935 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aee8db8a288190afd1e3b9dcf02e97 |
completed | March 9, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fb3a69908190ba8e7ac37c8ca0f8 |
completed | March 14, 2026, 6:07 a.m. |
Created at: March 9, 2026, 3:16 p.m.