Triple
T8509039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcel |
E201405
|
entity |
| Predicate | shortFormOf |
P43
|
FINISHED |
| Object | Marcellus |
E286568
|
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: Marcellus | Statement: [Marcel, shortFormOf, Marcellus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcellus Context triple: [Marcel, shortFormOf, Marcellus]
-
A.
Marcellus
Marcellus is a minor character in Shakespeare’s tragedy "Hamlet," a guard at Elsinore who is among the first to witness and report the appearance of the ghost of King Hamlet.
-
B.
Marcellus
chosen
Marcellus is a prominent ancient Roman cognomen associated with members of the patrician Claudian gens, notably borne by several distinguished statesmen and military leaders.
-
C.
Marcellus Wiley
Marcellus Wiley is a former NFL defensive end and later sports media personality who played college football at Columbia University.
-
D.
Tyrannus
Tyrannus is a genus of robust, often aggressive New World flycatchers known for their aerial insect hunting and territorial behavior.
-
E.
Sychaeus
Sychaeus is a wealthy Phoenician nobleman and priest of Hercules in Roman mythology, best known as the murdered husband of Queen Dido of Carthage.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5df74e8819086b1445cc907e371 |
completed | March 31, 2026, 3:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce88ec84208190ab72c8411e6cc4c2 |
completed | April 2, 2026, 3:19 p.m. |
Created at: March 30, 2026, 6:15 p.m.