Triple
T3519613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew McConaughey |
E74387
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Contact |
E321116
|
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: Contact | Statement: [Matthew McConaughey, notableWork, Contact]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Contact Context triple: [Matthew McConaughey, notableWork, Contact]
-
A.
Contact
Contact is a science fiction novel by Carl Sagan that explores humanity’s first communication with an extraterrestrial intelligence and the intersection of science, faith, and politics.
-
B.
Contact
chosen
Contact is a 1997 science fiction film, based on Carl Sagan’s novel, that follows a scientist’s first-contact encounter with extraterrestrial intelligence.
-
C.
Contact Publishing
Contact Publishing was a Dutch publishing house best known for originally bringing Anne Frank’s diary to the public.
-
D.
Conn
Conn is an Irish given name of ancient Gaelic origin, often associated with meanings like "chief" or "wisdom" and borne by several legendary and historical figures in Ireland.
-
E.
.me
.me is the country code top-level domain (ccTLD) assigned to Montenegro, widely used worldwide for personal and brandable web addresses.
- 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_69ad85cfb5c881909c9a2edd9d6043cc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc4af70c8190a7471f28e1efd7fd |
completed | March 8, 2026, 6:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b37e848d1c8190b100cb2e1218afbb |
completed | March 13, 2026, 3:03 a.m. |
Created at: March 8, 2026, 3:19 p.m.