Triple
T20684433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tydeus |
E508376
|
entity |
| Predicate | appearsIn |
P795
|
FINISHED |
| Object | Thebaid (Statius) |
—
|
NE NERFINISHED |
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: Thebaid (Statius) | Statement: [Tydeus, appearsIn, Thebaid (Statius)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thebaid (Statius) Context triple: [Tydeus, appearsIn, Thebaid (Statius)]
-
A.
Statius' Thebaid
chosen
Statius' Thebaid is a 1st-century Latin epic poem that retells the tragic conflict between the sons of Oedipus and the war of the Seven against Thebes.
-
B.
Heroides
Heroides is a collection of elegiac epistolary poems by the Roman poet Ovid, presented as fictional letters written by mythological heroines to their absent lovers.
-
C.
Metamorphoses
Metamorphoses is a play by Mary Zimmerman that reimagines classical Greek and Roman myths through visually striking, water-centered staging.
-
D.
Lays of Ancient Rome
Lays of Ancient Rome is a collection of narrative poems by Thomas Babington Macaulay that retell legendary episodes from early Roman history in a stirring, ballad-like style.
-
E.
Enneüs
Enneüs is a Dutch given name most notably borne by politician Enneüs Heerma.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beaae5608190ac8cc64aa4717d53 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 11:45 a.m.