Triple
T33926663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horace Manges |
E869770
|
entity |
| Predicate | hasNameInFirm |
P99201
|
FINISHED |
| Object | Weil, Gotshal & Manges LLP |
—
|
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: Weil, Gotshal & Manges LLP | Statement: [Horace Manges, hasNameInFirm, Weil, Gotshal & Manges LLP]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNameInFirm Context triple: [Horace Manges, hasNameInFirm, Weil, Gotshal & Manges LLP]
-
A.
hasNameInOrganization
chosen
Indicates that an entity is known by a particular name within the context of a specific organization.
-
B.
hasMemberFirm
Indicates that an organization includes another organization as one of its affiliated or constituent firms.
-
C.
nameIncorporatedIn
Indicates that an entity’s name explicitly includes or incorporates the name of another entity.
-
D.
hasCompanyName
Indicates that an entity is associated with or identified by a specific company name.
-
E.
hasOfficialNameContaining
Indicates that an entity’s official name includes a specified substring or sequence of characters.
- F. None of above.
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_69f349992c508190aa4afa24a086cc8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fee0b2da3c8190a3519d0564f2f32d |
completed | May 9, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69fee05b315c819081dfcbfb15273487 |
completed | May 9, 2026, 7:20 a.m. |
Created at: May 1, 2026, 1:49 a.m.