Triple
T15637825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene Morgan |
E375990
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Morgan |
E1067484
|
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: Morgan | Statement: [Irene Morgan, familyName, Morgan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Morgan Context triple: [Irene Morgan, familyName, Morgan]
-
A.
Morgan
Morgan is a 2016 science fiction horror film about a genetically engineered human hybrid whose violent behavior leads to a crisis among the scientists who created her.
-
B.
Morgan
Morgan is the party that successfully defended the constitutionality of a key provision of the Voting Rights Act in the landmark U.S. Supreme Court case Katzenbach v. Morgan.
-
C.
Morgan
Morgan is a given name used by the American documentary filmmaker Morgan Neville.
-
D.
Morgan
Morgan is a small city in northern Utah that serves as the administrative and commercial center of Morgan County.
-
E.
Morgan
chosen
Morgan is a common Welsh surname with deep cultural and historical roots in Wales and among people of Welsh descent.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04eba51f08190ac5d9de7fc89405a |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f4923ac8190a03fe1f2c878c27e |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:14 a.m.